Stop the war!
Остановите войну!
for scientists:
default search action
Search dblp for Publications
export results for "policy parameter"
@article{DBLP:journals/npl/SaglamMCK24, author = {Baturay Saglam and Furkan B. Mutlu and Dogan C. Cicek and Suleyman Serdar Kozat}, title = {Parameter-Free Reduction of the Estimation Bias in Deep Reinforcement Learning for Deterministic Policy Gradients}, journal = {Neural Process. Lett.}, volume = {56}, number = {2}, pages = {80}, year = {2024}, url = {https://doi.org/10.1007/s11063-024-11461-y}, doi = {10.1007/S11063-024-11461-Y}, timestamp = {Sat, 04 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/npl/SaglamMCK24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/swevo/KleinZS24, author = {Luk{\'{a}}s Klein and Ivan Zelinka and David Seidl}, title = {Optimizing parameters in swarm intelligence using reinforcement learning: An application of Proximal Policy Optimization to the iSOMA algorithm}, journal = {Swarm Evol. Comput.}, volume = {85}, pages = {101487}, year = {2024}, url = {https://doi.org/10.1016/j.swevo.2024.101487}, doi = {10.1016/J.SWEVO.2024.101487}, timestamp = {Tue, 21 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/swevo/KleinZS24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aistats/MondalA24, author = {Washim Uddin Mondal and Vaneet Aggarwal}, editor = {Sanjoy Dasgupta and Stephan Mandt and Yingzhen Li}, title = {Improved Sample Complexity Analysis of Natural Policy Gradient Algorithm with General Parameterization for Infinite Horizon Discounted Reward Markov Decision Processes}, booktitle = {International Conference on Artificial Intelligence and Statistics, 2-4 May 2024, Palau de Congressos, Valencia, Spain}, series = {Proceedings of Machine Learning Research}, volume = {238}, pages = {3097--3105}, publisher = {{PMLR}}, year = {2024}, url = {https://proceedings.mlr.press/v238/u-mondal24a.html}, timestamp = {Mon, 13 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aistats/MondalA24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2402-02042, author = {Qinbo Bai and Washim Uddin Mondal and Vaneet Aggarwal}, title = {Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm}, journal = {CoRR}, volume = {abs/2402.02042}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2402.02042}, doi = {10.48550/ARXIV.2402.02042}, eprinttype = {arXiv}, eprint = {2402.02042}, timestamp = {Fri, 09 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2402-02042.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2403-11062, author = {Yudong Luo and Yangchen Pan and Han Wang and Philip H. S. Torr and Pascal Poupart}, title = {A Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimization}, journal = {CoRR}, volume = {abs/2403.11062}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2403.11062}, doi = {10.48550/ARXIV.2403.11062}, eprinttype = {arXiv}, eprint = {2403.11062}, timestamp = {Mon, 08 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2403-11062.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/cor/VisentinPRT23, author = {Andrea Visentin and Steven D. Prestwich and Roberto Rossi and S. Armagan Tarim}, title = {Stochastic dynamic programming heuristic for the (R,s,S) policy parameters computation}, journal = {Comput. Oper. Res.}, volume = {158}, pages = {106289}, year = {2023}, url = {https://doi.org/10.1016/j.cor.2023.106289}, doi = {10.1016/J.COR.2023.106289}, timestamp = {Tue, 12 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/cor/VisentinPRT23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/eswa/ShenZHGL23, author = {Chun Shen and Sheng Zhu and Shuai Han and Xiaoyu Gong and Shuai L{\"{u}}}, title = {Guided deterministic policy optimization with gradient-free policy parameters information}, journal = {Expert Syst. Appl.}, volume = {231}, pages = {120693}, year = {2023}, url = {https://doi.org/10.1016/j.eswa.2023.120693}, doi = {10.1016/J.ESWA.2023.120693}, timestamp = {Tue, 07 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/eswa/ShenZHGL23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijcon/PakkhesalS23, author = {Sajjad Pakkhesal and Saeed Shamaghdari}, title = {SOS-based policy iteration for \emph{H\({}_{\mbox{{\(\infty\)}}}\)} control of polynomial systems with uncertain parameters}, journal = {Int. J. Control}, volume = {96}, number = {4}, pages = {1053--1066}, year = {2023}, url = {https://doi.org/10.1080/00207179.2022.2027523}, doi = {10.1080/00207179.2022.2027523}, timestamp = {Fri, 28 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijcon/PakkhesalS23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/soco/TabariS23, author = {Mahmoud Mohammad Rezapour Tabari and Reihaneh Safari}, title = {Development of water re-allocation policy under uncertainty conditions in the inflow to reservoir and demands parameters: a case study of Karaj AmirKabir dam}, journal = {Soft Comput.}, volume = {27}, number = {10}, pages = {6521--6547}, year = {2023}, url = {https://doi.org/10.1007/s00500-023-07885-8}, doi = {10.1007/S00500-023-07885-8}, timestamp = {Wed, 17 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/soco/TabariS23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aistats/PattathilZO23, author = {Sarath Pattathil and Kaiqing Zhang and Asuman E. Ozdaglar}, editor = {Francisco J. R. Ruiz and Jennifer G. Dy and Jan{-}Willem van de Meent}, title = {Symmetric (Optimistic) Natural Policy Gradient for Multi-Agent Learning with Parameter Convergence}, booktitle = {International Conference on Artificial Intelligence and Statistics, 25-27 April 2023, Palau de Congressos, Valencia, Spain}, series = {Proceedings of Machine Learning Research}, volume = {206}, pages = {5641--5685}, publisher = {{PMLR}}, year = {2023}, url = {https://proceedings.mlr.press/v206/pattathil23a.html}, timestamp = {Mon, 19 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aistats/PattathilZO23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/FuYGD023, author = {Haotian Fu and Jiayu Yao and Omer Gottesman and Finale Doshi{-}Velez and George Konidaris}, title = {Performance Bounds for Model and Policy Transfer in Hidden-parameter MDPs}, booktitle = {The Eleventh International Conference on Learning Representations, {ICLR} 2023, Kigali, Rwanda, May 1-5, 2023}, publisher = {OpenReview.net}, year = {2023}, url = {https://openreview.net/pdf?id=20gBzEzgtiI}, timestamp = {Fri, 30 Jun 2023 14:38:38 +0200}, biburl = {https://dblp.org/rec/conf/iclr/FuYGD023.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/AlfanoYR23, author = {Carlo Alfano and Rui Yuan and Patrick Rebeschini}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, title = {A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence}, booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, year = {2023}, url = {http://papers.nips.cc/paper\_files/paper/2023/hash/61a9278dfef5f871b5e472389f8d6fa1-Abstract-Conference.html}, timestamp = {Fri, 01 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/AlfanoYR23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2303-16548, author = {Deyue Li}, title = {Policy Gradient Methods for Discrete Time Linear Quadratic Regulator With Random Parameters}, journal = {CoRR}, volume = {abs/2303.16548}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2303.16548}, doi = {10.48550/ARXIV.2303.16548}, eprinttype = {arXiv}, eprint = {2303.16548}, timestamp = {Thu, 13 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2303-16548.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2305-19575, author = {Jiacai Liu and Jinchi Chen and Ke Wei}, title = {On the Linear Convergence of Policy Gradient under Hadamard Parameterization}, journal = {CoRR}, volume = {abs/2305.19575}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2305.19575}, doi = {10.48550/ARXIV.2305.19575}, eprinttype = {arXiv}, eprint = {2305.19575}, timestamp = {Tue, 06 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2305-19575.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-09872, author = {So Kuroki and Jiaxian Guo and Tatsuya Matsushima and Takuya Okubo and Masato Kobayashi and Yuya Ikeda and Ryosuke Takanami and Paul Yoo and Yutaka Matsuo and Yusuke Iwasawa}, title = {GenORM: Generalizable One-shot Rope Manipulation with Parameter-Aware Policy}, journal = {CoRR}, volume = {abs/2306.09872}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.09872}, doi = {10.48550/ARXIV.2306.09872}, eprinttype = {arXiv}, eprint = {2306.09872}, timestamp = {Thu, 22 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-09872.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-09051, author = {So Kuroki and Jiaxian Guo and Tatsuya Matsushima and Takuya Okubo and Masato Kobayashi and Yuya Ikeda and Ryosuke Takanami and Paul Yoo and Yutaka Matsuo and Yusuke Iwasawa}, title = {GenDOM: Generalizable One-shot Deformable Object Manipulation with Parameter-Aware Policy}, journal = {CoRR}, volume = {abs/2309.09051}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.09051}, doi = {10.48550/ARXIV.2309.09051}, eprinttype = {arXiv}, eprint = {2309.09051}, timestamp = {Fri, 22 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-09051.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2310-05053, author = {Lang Feng and Dong Xing and Junru Zhang and Gang Pan}, title = {{FP3O:} Enabling Proximal Policy Optimization in Multi-Agent Cooperation with Parameter-Sharing Versatility}, journal = {CoRR}, volume = {abs/2310.05053}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2310.05053}, doi = {10.48550/ARXIV.2310.05053}, eprinttype = {arXiv}, eprint = {2310.05053}, timestamp = {Fri, 20 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2310-05053.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2310-11677, author = {Washim Uddin Mondal and Vaneet Aggarwal}, title = {Improved Sample Complexity Analysis of Natural Policy Gradient Algorithm with General Parameterization for Infinite Horizon Discounted Reward Markov Decision Processes}, journal = {CoRR}, volume = {abs/2310.11677}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2310.11677}, doi = {10.48550/ARXIV.2310.11677}, eprinttype = {arXiv}, eprint = {2310.11677}, timestamp = {Fri, 27 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2310-11677.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@phdthesis{DBLP:phd/es/Daniel22, author = {Beatriz Cabrero Daniel}, title = {Automating crowd simulation: from parameter tuning to dynamic context-to-policy adaptation}, school = {Pompeu Fabra University, Spain}, year = {2022}, url = {http://hdl.handle.net/10803/673251}, timestamp = {Tue, 27 Sep 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/phd/es/Daniel22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/systems/WakelandH22, author = {Wayne W. Wakeland and Jack B. Homer}, title = {Addressing Parameter Uncertainty in a Health Policy Simulation Model Using Monte Carlo Sensitivity Methods}, journal = {Syst.}, volume = {10}, number = {6}, pages = {225}, year = {2022}, url = {https://doi.org/10.3390/systems10060225}, doi = {10.3390/SYSTEMS10060225}, timestamp = {Tue, 31 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/systems/WakelandH22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tmlr/ZhouHHZRFL22, author = {Kaichen Zhou and Lanqing Hong and Shoukang Hu and Fengwei Zhou and Binxin Ru and Jiashi Feng and Zhenguo Li}, title = {{DHA:} End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture}, journal = {Trans. Mach. Learn. Res.}, volume = {2022}, year = {2022}, url = {https://openreview.net/forum?id=MHOAEiTlen}, timestamp = {Fri, 19 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tmlr/ZhouHHZRFL22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tsg/SepulvedaAMS22, author = {Juan Sep{\'{u}}lveda and Alejandro Angulo and Fernando Mancilla{-}David and Alexandre Street}, title = {Robust Co-Optimization of Droop and Affine Policy Parameters in Active Distribution Systems With High Penetration of Photovoltaic Generation}, journal = {{IEEE} Trans. Smart Grid}, volume = {13}, number = {6}, pages = {4355--4366}, year = {2022}, url = {https://doi.org/10.1109/TSG.2022.3177947}, doi = {10.1109/TSG.2022.3177947}, timestamp = {Mon, 05 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/tsg/SepulvedaAMS22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/twc/FlaniganL22, author = {Katherine A. Flanigan and Jerome P. Lynch}, title = {Optimal Event-Based Policy for Remote Parameter Estimation in Wireless Sensing Architectures Under Resource Constraints}, journal = {{IEEE} Trans. Wirel. Commun.}, volume = {21}, number = {7}, pages = {5293--5304}, year = {2022}, url = {https://doi.org/10.1109/TWC.2021.3139289}, doi = {10.1109/TWC.2021.3139289}, timestamp = {Thu, 27 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/twc/FlaniganL22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2201-08832, author = {Wesley A. Suttle and Alec Koppel and Ji Liu}, title = {Occupancy Information Ratio: Infinite-Horizon, Information-Directed, Parameterized Policy Search}, journal = {CoRR}, volume = {abs/2201.08832}, year = {2022}, url = {https://arxiv.org/abs/2201.08832}, eprinttype = {arXiv}, eprint = {2201.08832}, timestamp = {Tue, 21 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-08832.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2202-03957, author = {Stephen James and Pieter Abbeel}, title = {Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning}, journal = {CoRR}, volume = {abs/2202.03957}, year = {2022}, url = {https://arxiv.org/abs/2202.03957}, eprinttype = {arXiv}, eprint = {2202.03957}, timestamp = {Thu, 10 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2202-03957.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-10073, author = {Trang H. Tran and Lam M. Nguyen and Katya Scheinberg}, title = {Finding Optimal Policy for Queueing Models: New Parameterization}, journal = {CoRR}, volume = {abs/2206.10073}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.10073}, doi = {10.48550/ARXIV.2206.10073}, eprinttype = {arXiv}, eprint = {2206.10073}, timestamp = {Tue, 28 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-10073.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2210-12812, author = {Sarath Pattathil and Kaiqing Zhang and Asuman E. Ozdaglar}, title = {Symmetric (Optimistic) Natural Policy Gradient for Multi-agent Learning with Parameter Convergence}, journal = {CoRR}, volume = {abs/2210.12812}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2210.12812}, doi = {10.48550/ARXIV.2210.12812}, eprinttype = {arXiv}, eprint = {2210.12812}, timestamp = {Fri, 28 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2210-12812.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/candie/HaghighiCM21, author = {Firoozeh Haghighi and Bruno Castanier and Hasan Misaii}, title = {Rolling horizon optimal maintenance policy for a system subject to shocks and degradation under uncertain parameters}, journal = {Comput. Ind. Eng.}, volume = {157}, pages = {107298}, year = {2021}, url = {https://doi.org/10.1016/j.cie.2021.107298}, doi = {10.1016/J.CIE.2021.107298}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/candie/HaghighiCM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/csysl/GravellGS21, author = {Benjamin Gravell and Karthik Ganapathy and Tyler H. Summers}, title = {Policy Iteration for Linear Quadratic Games With Stochastic Parameters}, journal = {{IEEE} Control. Syst. Lett.}, volume = {5}, number = {1}, pages = {307--312}, year = {2021}, url = {https://doi.org/10.1109/LCSYS.2020.3001883}, doi = {10.1109/LCSYS.2020.3001883}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/csysl/GravellGS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/eor/VisentinPRT21, author = {Andrea Visentin and Steve Prestwich and Roberto Rossi and S. Armagan Tarim}, title = {Computing optimal (R, s, {S)} policy parameters by a hybrid of branch-and-bound and stochastic dynamic programming}, journal = {Eur. J. Oper. Res.}, volume = {294}, number = {1}, pages = {91--99}, year = {2021}, url = {https://doi.org/10.1016/j.ejor.2021.01.012}, doi = {10.1016/J.EJOR.2021.01.012}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/eor/VisentinPRT21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tist/LiLSCYY21, author = {Shilei Li and Meng Li and Jiongming Su and Shaofei Chen and Zhimin Yuan and Qing Ye}, title = {{PP-PG:} Combining Parameter Perturbation with Policy Gradient Methods for Effective and Efficient Explorations in Deep Reinforcement Learning}, journal = {{ACM} Trans. Intell. Syst. Technol.}, volume = {12}, number = {3}, pages = {35:1--35:21}, year = {2021}, url = {https://doi.org/10.1145/3452008}, doi = {10.1145/3452008}, timestamp = {Wed, 01 Sep 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tist/LiLSCYY21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cdc/SunF21, author = {Yue Sun and Maryam Fazel}, title = {Learning Optimal Controllers by Policy Gradient: Global Optimality via Convex Parameterization}, booktitle = {2021 60th {IEEE} Conference on Decision and Control (CDC), Austin, TX, USA, December 14-17, 2021}, pages = {4576--4581}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/CDC45484.2021.9682821}, doi = {10.1109/CDC45484.2021.9682821}, timestamp = {Tue, 17 May 2022 15:53:17 +0200}, biburl = {https://dblp.org/rec/conf/cdc/SunF21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iecon/ArditiKUBO21, author = {Emir Arditi and Tjasa Kunavar and Emre Ugur and Jan Babic and Erhan {\"{O}}ztop}, title = {Inferring Cost Functions Using Reward Parameter Search and Policy Gradient Reinforcement Learning}, booktitle = {{IECON} 2021 - 47th Annual Conference of the {IEEE} Industrial Electronics Society, Toronto, ON, Canada, October 13-16, 2021}, pages = {1--6}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/IECON48115.2021.9589967}, doi = {10.1109/IECON48115.2021.9589967}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iecon/ArditiKUBO21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcci/GomezT21, author = {Alejandro de Miguel Gomez and Farshad Ghassemi Toosi}, editor = {Thomas B{\"{a}}ck and Christian Wagner and Jonathan M. Garibaldi and H. K. Lam and Marie Cottrell and Juan Juli{\'{a}}n Merelo and Kevin Warwick}, title = {Continuous Parameter Control in Genetic Algorithms using Policy Gradient Reinforcement Learning}, booktitle = {Proceedings of the 13th International Joint Conference on Computational Intelligence, {IJCCI} 2021, Online Streaming, October 25-27, 2021}, pages = {115--122}, publisher = {{SCITEPRESS}}, year = {2021}, url = {https://doi.org/10.5220/0010643500003063}, doi = {10.5220/0010643500003063}, timestamp = {Tue, 06 Jun 2023 14:58:01 +0200}, biburl = {https://dblp.org/rec/conf/ijcci/GomezT21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2105-13986, author = {Caleb M. Bowyer}, title = {Improving Generalization in Mountain Car Through the Partitioned Parameterized Policy Approach via Quasi-Stochastic Gradient Descent}, journal = {CoRR}, volume = {abs/2105.13986}, year = {2021}, url = {https://arxiv.org/abs/2105.13986}, eprinttype = {arXiv}, eprint = {2105.13986}, timestamp = {Tue, 01 Jun 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2105-13986.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2109-05765, author = {Kaichen Zhou and Lanqing Hong and Shoukang Hu and Fengwei Zhou and Binxin Ru and Jiashi Feng and Zhenguo Li}, title = {{DHA:} End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture}, journal = {CoRR}, volume = {abs/2109.05765}, year = {2021}, url = {https://arxiv.org/abs/2109.05765}, eprinttype = {arXiv}, eprint = {2109.05765}, timestamp = {Tue, 21 Sep 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2109-05765.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2110-15799, author = {Benjamin A. Spiegel and George Konidaris}, title = {Guided Policy Search for Parameterized Skills using Adverbs}, journal = {CoRR}, volume = {abs/2110.15799}, year = {2021}, url = {https://arxiv.org/abs/2110.15799}, eprinttype = {arXiv}, eprint = {2110.15799}, timestamp = {Tue, 02 Nov 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2110-15799.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/rfc/rfc9029, author = {Adrian Farrel}, title = {Updates to the Allocation Policy for the Border Gateway Protocol - Link State {(BGP-LS)} Parameters Registries}, journal = {{RFC}}, volume = {9029}, pages = {1--5}, year = {2021}, url = {https://doi.org/10.17487/RFC9029}, doi = {10.17487/RFC9029}, timestamp = {Wed, 09 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/rfc/rfc9029.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/access/AhmedAMJH20, author = {Bilal Ahmed and Nadeem Ahmed and Asad Waqar Malik and Mohsin Jafri and Taimur Hafeez}, title = {Fingerprinting {SDN} Policy Parameters: An Empirical Study}, journal = {{IEEE} Access}, volume = {8}, pages = {142379--142392}, year = {2020}, url = {https://doi.org/10.1109/ACCESS.2020.3012176}, doi = {10.1109/ACCESS.2020.3012176}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/access/AhmedAMJH20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/eaai/LiuLSWH20, author = {Tundong Liu and Liduan Li and Guifang Shao and Xiaomin Wu and Meng Huang}, title = {A novel policy gradient algorithm with PSO-based parameter exploration for continuous control}, journal = {Eng. Appl. Artif. Intell.}, volume = {90}, pages = {103525}, year = {2020}, url = {https://doi.org/10.1016/j.engappai.2020.103525}, doi = {10.1016/J.ENGAPPAI.2020.103525}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/eaai/LiuLSWH20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/eor/OmshiGS20, author = {E. Mosayebi Omshi and Antoine Grall and Soudabeh Shemehsavar}, title = {A dynamic auto-adaptive predictive maintenance policy for degradation with unknown parameters}, journal = {Eur. J. Oper. Res.}, volume = {282}, number = {1}, pages = {81--92}, year = {2020}, url = {https://doi.org/10.1016/j.ejor.2019.08.050}, doi = {10.1016/J.EJOR.2019.08.050}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/eor/OmshiGS20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijpr/SgarbossaZFC20, author = {Fabio Sgarbossa and Ilenia Zennaro and Eleonora Florian and Martina Calzavara}, title = {Age replacement policy in the case of no data: the effect of Weibull parameter estimation}, journal = {Int. J. Prod. Res.}, volume = {58}, number = {19}, pages = {5851--5869}, year = {2020}, url = {https://doi.org/10.1080/00207543.2019.1660824}, doi = {10.1080/00207543.2019.1660824}, timestamp = {Wed, 07 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijpr/SgarbossaZFC20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijsysc/HanF20, author = {Kezhen Han and Jian Feng}, title = {Fault tolerant tracking control for a class of linear parameter varying systems using reduced-order simultaneous estimator and optimal preview policy}, journal = {Int. J. Syst. Sci.}, volume = {51}, number = {2}, pages = {313--333}, year = {2020}, url = {https://doi.org/10.1080/00207721.2019.1704096}, doi = {10.1080/00207721.2019.1704096}, timestamp = {Fri, 08 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ijsysc/HanF20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tinstmc/RenDZ020, author = {He Ren and Jing Dai and Huaguang Zhang and Kun Zhang}, title = {Off-policy integral reinforcement learning algorithm in dealing with nonzero sum game for nonlinear distributed parameter systems}, journal = {Trans. Inst. Meas. Control}, volume = {42}, number = {15}, pages = {2919--2928}, year = {2020}, url = {https://doi.org/10.1177/0142331220932634}, doi = {10.1177/0142331220932634}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tinstmc/RenDZ020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/fuzzIEEE/SachanD20, author = {Swati Sachan and Nishant Donchak}, title = {Generalized Stochastic Petri-Net Algorithm with Fuzzy Parameters to Evaluate Infrastructure Asset Management Policy}, booktitle = {29th {IEEE} International Conference on Fuzzy Systems, {FUZZ-IEEE} 2020, Glasgow, UK, July 19-24, 2020}, pages = {1--8}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/FUZZ48607.2020.9177562}, doi = {10.1109/FUZZ48607.2020.9177562}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/fuzzIEEE/SachanD20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcnn/Hosino20, author = {Tikara Hosino}, title = {Variational Bayesian Parameter-Based Policy Exploration}, booktitle = {2020 International Joint Conference on Neural Networks, {IJCNN} 2020, Glasgow, United Kingdom, July 19-24, 2020}, pages = {1--7}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/IJCNN48605.2020.9207091}, doi = {10.1109/IJCNN48605.2020.9207091}, timestamp = {Tue, 06 Oct 2020 15:44:04 +0200}, biburl = {https://dblp.org/rec/conf/ijcnn/Hosino20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/PossasB0FR20, author = {Rafael Possas and Lucas Barcelos and Rafael Oliveira and Dieter Fox and Fabio Ramos}, title = {Online BayesSim for Combined Simulator Parameter Inference and Policy Improvement}, booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2020, Las Vegas, NV, USA, October 24, 2020 - January 24, 2021}, pages = {5445--5452}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/IROS45743.2020.9341401}, doi = {10.1109/IROS45743.2020.9341401}, timestamp = {Tue, 18 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/PossasB0FR20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/wpes/SomeR20, author = {Doli{\`{e}}re Francis Som{\'{e}} and Tamara Rezk}, editor = {Jay Ligatti and Xinming Ou and Wouter Lueks and Paul Syverson}, title = {Strenghtening Content Security Policy via Monitoring and {URL} Parameters Filtering}, booktitle = {WPES'20: Proceedings of the 19th Workshop on Privacy in the Electronic Society, Virtual Event, USA, November 9, 2020}, pages = {1--13}, publisher = {{ACM}}, year = {2020}, url = {https://doi.org/10.1145/3411497.3420222}, doi = {10.1145/3411497.3420222}, timestamp = {Wed, 16 Dec 2020 15:24:47 +0100}, biburl = {https://dblp.org/rec/conf/wpes/SomeR20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2006-07554, author = {Yunhao Tang and Krzysztof Choromanski}, title = {Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies}, journal = {CoRR}, volume = {abs/2006.07554}, year = {2020}, url = {https://arxiv.org/abs/2006.07554}, eprinttype = {arXiv}, eprint = {2006.07554}, timestamp = {Wed, 17 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2006-07554.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2012-03532, author = {Alessandro Sestini and Alexander Kuhnle and Andrew D. Bagdanov}, title = {Deep Policy Networks for {NPC} Behaviors that Adapt to Changing Design Parameters in Roguelike Games}, journal = {CoRR}, volume = {abs/2012.03532}, year = {2020}, url = {https://arxiv.org/abs/2012.03532}, eprinttype = {arXiv}, eprint = {2012.03532}, timestamp = {Wed, 09 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2012-03532.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/infor/ChangCYZ19, author = {Chin{-}Chih Chang and Yen{-}Luan Chen and Xiaoling Yin and Zhe George Zhang}, title = {Generalized multi-parameter preventive replacement policy for systems with random processing times}, journal = {{INFOR} Inf. Syst. Oper. Res.}, volume = {57}, number = {2}, pages = {187--203}, year = {2019}, url = {https://doi.org/10.1080/03155986.2018.1533210}, doi = {10.1080/03155986.2018.1533210}, timestamp = {Thu, 16 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/infor/ChangCYZ19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/puc/ValmassoiGSKP19, author = {Arianna Valmassoi and Salem Gharbia and Silvana Di Sabatino and Prashant Kumar and Francesco Pilla}, title = {Future impacts of the reforestation policy on the atmospheric parameters in Ireland: a sensitivity study including heat discomfort impacts on humans and livestock}, journal = {Pers. Ubiquitous Comput.}, volume = {23}, number = {5-6}, pages = {707--721}, year = {2019}, url = {https://doi.org/10.1007/s00779-018-1160-3}, doi = {10.1007/S00779-018-1160-3}, timestamp = {Thu, 09 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/puc/ValmassoiGSKP19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ccta/OhKHKLKLLC19, author = {Tae{-}Ho Oh and Tae{-}Il Kim and Ji{-}Seok Han and Young{-}Seok Kim and Ji{-}Hyung Lee and Sang{-}Oh Kim and Sang{-}Sub Lee and Sang{-}Hoon Lee and Dong{-}Il Dan Cho}, title = {Deep Deterministic Policy Gradient-based Parameter Selection Method of Notch Filters for Suppressing Mechanical Resonance in Industrial Servo Systems}, booktitle = {2019 {IEEE} Conference on Control Technology and Applications, {CCTA} 2019, Hong Kong, SAR, China, August 19-21, 2019}, pages = {320--324}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/CCTA.2019.8920682}, doi = {10.1109/CCTA.2019.8920682}, timestamp = {Tue, 14 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ccta/OhKHKLKLLC19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/LiGWSH19, author = {Minhan Li and Xiang Gao and Yue Wen and Jennie Si and He Helen Huang}, title = {Offline Policy Iteration Based Reinforcement Learning Controller for Online Robotic Knee Prosthesis Parameter Tuning}, booktitle = {International Conference on Robotics and Automation, {ICRA} 2019, Montreal, QC, Canada, May 20-24, 2019}, pages = {2831--2837}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICRA.2019.8794212}, doi = {10.1109/ICRA.2019.8794212}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/LiGWSH19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ictc/JungBLKP19, author = {Joonyoung Jung and Jang Won Bae and Chun{-}Hee Lee and Dong{-}oh Kang and Euihyun Paik}, title = {{GBM} based Policy Influence Analysis of Agent Simulation Parameters}, booktitle = {2019 International Conference on Information and Communication Technology Convergence, {ICTC} 2019, Jeju Island, Korea (South), October 16-18, 2019}, pages = {1324--1326}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICTC46691.2019.8939694}, doi = {10.1109/ICTC46691.2019.8939694}, timestamp = {Tue, 07 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ictc/JungBLKP19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ro-man/PrakashVB19, author = {Ravi Prakash and Mohit Vohra and Laxmidhar Behera}, title = {Learning Optimal Parameterized Policy for High Level Strategies in a Game Setting}, booktitle = {28th {IEEE} International Conference on Robot and Human Interactive Communication, {RO-MAN} 2019, New Delhi, India, October 14-18, 2019}, pages = {1--6}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/RO-MAN46459.2019.8956383}, doi = {10.1109/RO-MAN46459.2019.8956383}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ro-man/PrakashVB19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/firai/QueisserS18, author = {Jeffrey F. Queisser and Jochen J. Steil}, title = {Bootstrapping of Parameterized Skills Through Hybrid Optimization in Task and Policy Spaces}, journal = {Frontiers Robotics {AI}}, volume = {5}, pages = {49}, year = {2018}, url = {https://doi.org/10.3389/frobt.2018.00049}, doi = {10.3389/FROBT.2018.00049}, timestamp = {Tue, 16 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/firai/QueisserS18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijrsda/SinghPNS18, author = {Trailokyanath Singh and Hadibandhu Pattanayak and Ameeya Kumar Nayak and Nirakar Niranjan Sethy}, title = {An Optimal Policy with Three-Parameter Weibull Distribution Deterioration, Quadratic Demand, and Salvage Value Under Partial Backlogging}, journal = {Int. J. Rough Sets Data Anal.}, volume = {5}, number = {1}, pages = {79--98}, year = {2018}, url = {https://doi.org/10.4018/IJRSDA.2018010106}, doi = {10.4018/IJRSDA.2018010106}, timestamp = {Thu, 16 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijrsda/SinghPNS18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ior/VercraeneGK18, author = {Samuel Vercraene and Jean{-}Philippe Gayon and Fikri Karaesmen}, title = {Effects of System Parameters on the Optimal Cost and Policy in a Class of Multidimensional Queueing Control Problems}, journal = {Oper. Res.}, volume = {66}, number = {1}, pages = {150--162}, year = {2018}, url = {https://doi.org/10.1287/opre.2017.1600}, doi = {10.1287/OPRE.2017.1600}, timestamp = {Tue, 01 Jun 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ior/VercraeneGK18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ccgrid/ChunduriGLSN18, author = {Sudheer Chunduri and Meysam Ghaffari and Mehran Sadeghi Lahijani and Ashok Srinivasan and Sirish Namilae}, editor = {Esam El{-}Araby and Dhabaleswar K. Panda and Sandra Gesing and Amy W. Apon and Volodymyr V. Kindratenko and Massimo Cafaro and Alfredo Cuzzocrea}, title = {Parallel Low Discrepancy Parameter Sweep for Public Health Policy}, booktitle = {18th {IEEE/ACM} International Symposium on Cluster, Cloud and Grid Computing, {CCGRID} 2018, Washington, DC, USA, May 1-4, 2018}, pages = {291--300}, publisher = {{IEEE} Computer Society}, year = {2018}, url = {https://doi.org/10.1109/CCGRID.2018.00044}, doi = {10.1109/CCGRID.2018.00044}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ccgrid/ChunduriGLSN18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/gecco/OhashiFSA18, author = {Kyotaro Ohashi and Natsuki Fujiyoshi and Naoki Sakamoto and Youhei Akimoto}, editor = {Hern{\'{a}}n E. Aguirre and Keiki Takadama}, title = {Model parameter adaptive instance-based policy optimization for episodic control tasks of nonholonomic systems}, booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference Companion, {GECCO} 2018, Kyoto, Japan, July 15-19, 2018}, pages = {1426--1433}, publisher = {{ACM}}, year = {2018}, url = {https://doi.org/10.1145/3205651.3208295}, doi = {10.1145/3205651.3208295}, timestamp = {Sat, 19 Oct 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/gecco/OhashiFSA18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccsip/GaoWLSH18, author = {Xiang Gao and Yue Wen and Minhan Li and Jennie Si and He (Helen) Huang}, editor = {Fuchun Sun and Huaping Liu and Dewen Hu}, title = {Robotic Knee Parameter Tuning Using Approximate Policy Iteration}, booktitle = {Cognitive Systems and Signal Processing - 4th International Conference, {ICCSIP} 2018, Beijing, China, November 29 - December 1, 2018, Revised Selected Papers, Part {I}}, series = {Communications in Computer and Information Science}, volume = {1005}, pages = {554--563}, publisher = {Springer}, year = {2018}, url = {https://doi.org/10.1007/978-981-13-7983-3\_49}, doi = {10.1007/978-981-13-7983-3\_49}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iccsip/GaoWLSH18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/Chatzilygeroudis18, author = {Konstantinos I. Chatzilygeroudis and Jean{-}Baptiste Mouret}, title = {Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics}, booktitle = {2018 {IEEE} International Conference on Robotics and Automation, {ICRA} 2018, Brisbane, Australia, May 21-25, 2018}, pages = {1--9}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICRA.2018.8461083}, doi = {10.1109/ICRA.2018.8461083}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/icra/Chatzilygeroudis18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/IshigeUTK18, author = {Matthew Ishige and Takuya Umedachi and Tadahiro Taniguchi and Yoshihiro Kawahara}, title = {Learning Oscillator-Based Gait Controller for String-Form Soft Robots Using Parameter-Exploring Policy Gradients}, booktitle = {2018 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2018, Madrid, Spain, October 1-5, 2018}, pages = {6445--6452}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/IROS.2018.8594338}, doi = {10.1109/IROS.2018.8594338}, timestamp = {Wed, 17 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/IshigeUTK18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/safecomp/BehzadanM18, author = {Vahid Behzadan and Arslan Munir}, editor = {Barbara Gallina and Amund Skavhaug and Erwin Schoitsch and Friedemann Bitsch}, title = {Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise}, booktitle = {Computer Safety, Reliability, and Security - {SAFECOMP} 2018 Workshops, ASSURE, DECSoS, SASSUR, STRIVE, and WAISE, V{\"{a}}ster{\aa}s, Sweden, September 18, 2018, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {11094}, pages = {406--417}, publisher = {Springer}, year = {2018}, url = {https://doi.org/10.1007/978-3-319-99229-7\_34}, doi = {10.1007/978-3-319-99229-7\_34}, timestamp = {Tue, 14 May 2019 10:00:44 +0200}, biburl = {https://dblp.org/rec/conf/safecomp/BehzadanM18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1806-02190, author = {Vahid Behzadan and Arslan Munir}, title = {Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise}, journal = {CoRR}, volume = {abs/1806.02190}, year = {2018}, url = {http://arxiv.org/abs/1806.02190}, eprinttype = {arXiv}, eprint = {1806.02190}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1806-02190.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ant/ValmassoiGSSP17, author = {Arianna Valmassoi and Salem Gharbia and Santa Stibe and Silvana Di Sabatino and Francesco Pilla}, editor = {Elhadi M. Shakshuki}, title = {Future Impacts of the Reforestation Policy on the amospheric parameters: a sensitivity study over Ireland}, booktitle = {The 8th International Conference on Ambient Systems, Networks and Technologies {(ANT} 2017) / The 7th International Conference on Sustainable Energy Information Technology {(SEIT} 2017), 16-19 May 2017, Madeira, Portugal}, series = {Procedia Computer Science}, volume = {109}, pages = {367--375}, publisher = {Elsevier}, year = {2017}, url = {https://doi.org/10.1016/j.procs.2017.05.403}, doi = {10.1016/J.PROCS.2017.05.403}, timestamp = {Thu, 08 Jul 2021 16:04:01 +0200}, biburl = {https://dblp.org/rec/conf/ant/ValmassoiGSSP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1709-06917, author = {Konstantinos I. Chatzilygeroudis and Jean{-}Baptiste Mouret}, title = {Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics}, journal = {CoRR}, volume = {abs/1709.06917}, year = {2017}, url = {http://arxiv.org/abs/1709.06917}, eprinttype = {arXiv}, eprint = {1709.06917}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1709-06917.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1710-00336, author = {Xiangxiang Chu and Hangjun Ye}, title = {Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning}, journal = {CoRR}, volume = {abs/1710.00336}, year = {2017}, url = {http://arxiv.org/abs/1710.00336}, eprinttype = {arXiv}, eprint = {1710.00336}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1710-00336.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/alr/WangUD16, author = {Jiexin Wang and Eiji Uchibe and Kenji Doya}, title = {EM-based policy hyper parameter exploration: application to standing and balancing of a two-wheeled smartphone robot}, journal = {Artif. Life Robotics}, volume = {21}, number = {1}, pages = {125--131}, year = {2016}, url = {https://doi.org/10.1007/s10015-015-0260-7}, doi = {10.1007/S10015-015-0260-7}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/alr/WangUD16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jota/ChengZFW16, author = {Kang Cheng and Kanjian Zhang and Shumin Fei and Haikun Wei}, title = {Potential-Based Least-Squares Policy Iteration for a Parameterized Feedback Control System}, journal = {J. Optim. Theory Appl.}, volume = {169}, number = {2}, pages = {692--704}, year = {2016}, url = {https://doi.org/10.1007/s10957-015-0809-6}, doi = {10.1007/S10957-015-0809-6}, timestamp = {Tue, 07 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jota/ChengZFW16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/sttt/RaniseTT16, author = {Silvio Ranise and Anh Tuan Truong and Riccardo Traverso}, title = {Parameterized model checking for security policy analysis}, journal = {Int. J. Softw. Tools Technol. Transf.}, volume = {18}, number = {5}, pages = {559--573}, year = {2016}, url = {https://doi.org/10.1007/s10009-015-0410-1}, doi = {10.1007/S10009-015-0410-1}, timestamp = {Tue, 16 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/sttt/RaniseTT16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/arobots/ReinhartS15, author = {Ren{\'{e}} Felix Reinhart and Jochen Jakob Steil}, title = {Efficient policy search in low-dimensional embedding spaces by generalizing motion primitives with a parameterized skill memory}, journal = {Auton. Robots}, volume = {38}, number = {4}, pages = {331--348}, year = {2015}, url = {https://doi.org/10.1007/s10514-014-9417-9}, doi = {10.1007/S10514-014-9417-9}, timestamp = {Thu, 18 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/arobots/ReinhartS15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijsysc/MovahedZ15, author = {Kamran Karimi Movahed and Zhi{-}Hai Zhang}, title = {Robust design of (\emph{s}, \emph{S}) inventory policy parameters in supply chains with demand and lead time uncertainties}, journal = {Int. J. Syst. Sci.}, volume = {46}, number = {12}, pages = {2258--2268}, year = {2015}, url = {https://doi.org/10.1080/00207721.2013.860637}, doi = {10.1080/00207721.2013.860637}, timestamp = {Wed, 22 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijsysc/MovahedZ15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijsysc/YangC15, author = {Dong{-}Yuh Yang and Po{-}Kai Chang}, title = {A parametric programming solution to the \emph{F}-policy queue with fuzzy parameters}, journal = {Int. J. Syst. Sci.}, volume = {46}, number = {4}, pages = {590--598}, year = {2015}, url = {https://doi.org/10.1080/00207721.2013.792975}, doi = {10.1080/00207721.2013.792975}, timestamp = {Wed, 22 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijsysc/YangC15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icarsc/AbdolmalekiLR0N15, author = {Abbas Abdolmaleki and Nuno Lau and Lu{\'{\i}}s Paulo Reis and Jan Peters and Gerhard Neumann}, title = {Contextual Policy Search for Generalizing a Parameterized Biped Walking Controller}, booktitle = {2015 {IEEE} International Conference on Autonomous Robot Systems and Competitions, {ICARSC} 2015, Vila Real, Portugal, April 8-10, 2015}, pages = {17--22}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICARSC.2015.43}, doi = {10.1109/ICARSC.2015.43}, timestamp = {Wed, 16 Oct 2019 14:14:57 +0200}, biburl = {https://dblp.org/rec/conf/icarsc/AbdolmalekiLR0N15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcnn/ManganiniPRB15, author = {Giorgio Manganini and Matteo Pirotta and Marcello Restelli and Luca Bascetta}, title = {Following Newton direction in Policy Gradient with parameter exploration}, booktitle = {2015 International Joint Conference on Neural Networks, {IJCNN} 2015, Killarney, Ireland, July 12-17, 2015}, pages = {1--8}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/IJCNN.2015.7280673}, doi = {10.1109/IJCNN.2015.7280673}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ijcnn/ManganiniPRB15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ssci/VaerenberghHDMN15, author = {Kevin Van Vaerenbergh and Yann{-}Micha{\"{e}}l De Hauwere and Bruno Depraetere and Kristof Van Moffaert and Ann Now{\'{e}}}, title = {A Policy Gradient with Parameter-Based Exploration Approach for Zone-Heating}, booktitle = {{IEEE} Symposium Series on Computational Intelligence, {SSCI} 2015, Cape Town, South Africa, December 7-10, 2015}, pages = {556--563}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/SSCI.2015.88}, doi = {10.1109/SSCI.2015.88}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ssci/VaerenberghHDMN15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/TangkarattMZMS14, author = {Voot Tangkaratt and Syogo Mori and Tingting Zhao and Jun Morimoto and Masashi Sugiyama}, title = {Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation}, journal = {Neural Networks}, volume = {57}, pages = {128--140}, year = {2014}, url = {https://doi.org/10.1016/j.neunet.2014.06.006}, doi = {10.1016/J.NEUNET.2014.06.006}, timestamp = {Mon, 07 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/nn/TangkarattMZMS14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/ReinhartS14, author = {Ren{\'{e}} Felix Reinhart and Jochen Jakob Steil}, title = {Efficient policy search with a parameterized skill memory}, booktitle = {2014 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2014, Chicago, IL, USA, September 14-18, 2014}, pages = {1400--1407}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/IROS.2014.6942740}, doi = {10.1109/IROS.2014.6942740}, timestamp = {Tue, 05 Sep 2023 15:07:47 +0200}, biburl = {https://dblp.org/rec/conf/iros/ReinhartS14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/eor/InderfurthKK13, author = {Karl Inderfurth and Peter Kelle and Rainer Kleber}, title = {Dual sourcing using capacity reservation and spot market: Optimal procurement policy and heuristic parameter determination}, journal = {Eur. J. Oper. Res.}, volume = {225}, number = {2}, pages = {298--309}, year = {2013}, url = {https://doi.org/10.1016/j.ejor.2012.08.025}, doi = {10.1016/J.EJOR.2012.08.025}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/eor/InderfurthKK13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/neco/ZhaoHTMS13, author = {Tingting Zhao and Hirotaka Hachiya and Voot Tangkaratt and Jun Morimoto and Masashi Sugiyama}, title = {Efficient Sample Reuse in Policy Gradients with Parameter-Based Exploration}, journal = {Neural Comput.}, volume = {25}, number = {6}, pages = {1512--1547}, year = {2013}, url = {https://doi.org/10.1162/NECO\_a\_00452}, doi = {10.1162/NECO\_A\_00452}, timestamp = {Mon, 07 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/neco/ZhaoHTMS13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/soco/NiL13, author = {Yaodong Ni and Zhi{-}Qiang Liu}, title = {Policy iteration for bounded-parameter POMDPs}, journal = {Soft Comput.}, volume = {17}, number = {4}, pages = {537--548}, year = {2013}, url = {https://doi.org/10.1007/s00500-012-0932-3}, doi = {10.1007/S00500-012-0932-3}, timestamp = {Sat, 20 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/soco/NiL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/IEEEcloud/KikuchiUKM13, author = {Shinji Kikuchi and Tetsuya Uchiumi and Shinya Kitajima and Yasuhide Matsumoto}, title = {Configuration Policy Extraction for Parameter Settings in Cloud Infrastructure Using {UML/OCL} Verification}, booktitle = {2013 {IEEE} Sixth International Conference on Cloud Computing, Santa Clara, CA, USA, June 28 - July 3, 2013}, pages = {67--74}, publisher = {{IEEE} Computer Society}, year = {2013}, url = {https://doi.org/10.1109/CLOUD.2013.51}, doi = {10.1109/CLOUD.2013.51}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/IEEEcloud/KikuchiUKM13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apnoms/KimPJ13, author = {Hyeonwoo Kim and Wooguil Pak and Hongtaek Ju}, title = {Correlation analysis between inference accuracy and inference parameters for stateless firewall policy}, booktitle = {15th Asia-Pacific Network Operations and Management Symposium, {APNOMS} 2013, Hiroshima, Japan, September 25-27, 2013}, pages = {1--6}, publisher = {{IEEE}}, year = {2013}, url = {https://ieeexplore.ieee.org/document/6665274/}, timestamp = {Sun, 08 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apnoms/KimPJ13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ascc/XiaJ13, author = {Li Xia and Qing{-}Shan Jia}, title = {Policy iteration for parameterized Markov decision processes and its application}, booktitle = {9th Asian Control Conference, {ASCC} 2013, Istanbul, Turkey, June 23-26, 2013}, pages = {1--6}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ASCC.2013.6606023}, doi = {10.1109/ASCC.2013.6606023}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ascc/XiaJ13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icann/Sehnke13, author = {Frank Sehnke}, editor = {Valeri M. Mladenov and Petia D. Koprinkova{-}Hristova and G{\"{u}}nther Palm and Alessandro E. P. Villa and Bruno Appollini and Nikola K. Kasabov}, title = {Efficient Baseline-Free Sampling in Parameter Exploring Policy Gradients: Super Symmetric {PGPE}}, booktitle = {Artificial Neural Networks and Machine Learning - {ICANN} 2013 - 23rd International Conference on Artificial Neural Networks, Sofia, Bulgaria, September 10-13, 2013. Proceedings}, series = {Lecture Notes in Computer Science}, volume = {8131}, pages = {130--137}, publisher = {Springer}, year = {2013}, url = {https://doi.org/10.1007/978-3-642-40728-4\_17}, doi = {10.1007/978-3-642-40728-4\_17}, timestamp = {Thu, 04 Jun 2020 19:07:57 +0200}, biburl = {https://dblp.org/rec/conf/icann/Sehnke13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/MoriTZMS13, author = {Syogo Mori and Voot Tangkaratt and Tingting Zhao and Jun Morimoto and Masashi Sugiyama}, title = {Model-Based Policy Gradients with Parameter-Based Exploration by Least-Squares Conditional Density Estimation}, journal = {CoRR}, volume = {abs/1307.5118}, year = {2013}, url = {http://arxiv.org/abs/1307.5118}, eprinttype = {arXiv}, eprint = {1307.5118}, timestamp = {Mon, 07 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/MoriTZMS13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/Sehnke13, author = {Frank Sehnke}, title = {Efficient Baseline-free Sampling in Parameter Exploring Policy Gradients: Super Symmetric {PGPE}}, journal = {CoRR}, volume = {abs/1312.3811}, year = {2013}, url = {http://arxiv.org/abs/1312.3811}, eprinttype = {arXiv}, eprint = {1312.3811}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/Sehnke13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1301-3966, author = {Tingting Zhao and Hirotaka Hachiya and Voot Tangkaratt and Jun Morimoto and Masashi Sugiyama}, title = {Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration}, journal = {CoRR}, volume = {abs/1301.3966}, year = {2013}, url = {http://arxiv.org/abs/1301.3966}, eprinttype = {arXiv}, eprint = {1301.3966}, timestamp = {Mon, 07 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1301-3966.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@phdthesis{DBLP:phd/dnb/Sehnke12, author = {Frank Sehnke}, title = {Parameter exploring policy gradients and their implications}, school = {Technical University Munich}, year = {2012}, url = {https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20121030-1099128-0-7}, urn = {urn:nbn:de:bvb:91-diss-20121030-1099128-0-7}, timestamp = {Sat, 17 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/phd/dnb/Sehnke12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tac/JettoO12, author = {Leopoldo Jetto and Valentina Orsini}, title = {A Supervised Switching Control Policy for {LPV} Systems With Inaccurate Parameter Knowledge}, journal = {{IEEE} Trans. Autom. Control.}, volume = {57}, number = {6}, pages = {1527--1532}, year = {2012}, url = {https://doi.org/10.1109/TAC.2011.2174690}, doi = {10.1109/TAC.2011.2174690}, timestamp = {Wed, 20 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tac/JettoO12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tnsm/SamakA12, author = {Taghrid Samak and Ehab Al{-}Shaer}, title = {Fuzzy Conflict Analysis for QoS Policy Parameters in DiffServ Networks}, journal = {{IEEE} Trans. Netw. Serv. Manag.}, volume = {9}, number = {4}, pages = {459--472}, year = {2012}, url = {https://doi.org/10.1109/TNSM.2012.062512.120308}, doi = {10.1109/TNSM.2012.062512.120308}, timestamp = {Thu, 27 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tnsm/SamakA12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/MisuK12, author = {Teruhisa Misu and Hideki Kashioka}, title = {Simultaneous feature selection and parameter optimization for training of dialog policy by reinforcement learning}, booktitle = {2012 {IEEE} Spoken Language Technology Workshop (SLT), Miami, FL, USA, December 2-5, 2012}, pages = {1--6}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/SLT.2012.6424160}, doi = {10.1109/SLT.2012.6424160}, timestamp = {Wed, 16 Oct 2019 14:14:53 +0200}, biburl = {https://dblp.org/rec/conf/slt/MisuK12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/candie/NevesSM11, author = {Maxstaley L. Neves and Leonardo P. Santiago and Carlos A. Maia}, title = {A condition-based maintenance policy and input parameters estimation for deteriorating systems under periodic inspection}, journal = {Comput. Ind. Eng.}, volume = {61}, number = {3}, pages = {503--511}, year = {2011}, url = {https://doi.org/10.1016/j.cie.2011.04.005}, doi = {10.1016/J.CIE.2011.04.005}, timestamp = {Thu, 20 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/candie/NevesSM11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/cor/PaulR11, author = {Brijesh Paul and Chandrasekharan Rajendran}, title = {Rationing mechanisms and inventory control-policy parameters for a divergent supply chain operating with lost sales and costs of review}, journal = {Comput. Oper. Res.}, volume = {38}, number = {8}, pages = {1117--1130}, year = {2011}, url = {https://doi.org/10.1016/j.cor.2010.11.002}, doi = {10.1016/J.COR.2010.11.002}, timestamp = {Tue, 18 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/cor/PaulR11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/infocom/WeinsbergSM11, author = {Udi Weinsberg and Augustin Soule and Laurent Massouli{\'{e}}}, title = {Inferring traffic shaping and policy parameters using end host measurements}, booktitle = {{INFOCOM} 2011. 30th {IEEE} International Conference on Computer Communications, Joint Conference of the {IEEE} Computer and Communications Societies, 10-15 April 2011, Shanghai, China}, pages = {151--155}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/INFCOM.2011.5934941}, doi = {10.1109/INFCOM.2011.5934941}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/infocom/WeinsbergSM11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/KormushevUCTC11, author = {Petar Kormushev and Barkan Ugurlu and Sylvain Calinon and Nikolaos G. Tsagarakis and Darwin G. Caldwell}, title = {Bipedal walking energy minimization by reinforcement learning with evolving policy parameterization}, booktitle = {2011 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2011, San Francisco, CA, USA, September 25-30, 2011}, pages = {318--324}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/IROS.2011.6094427}, doi = {10.1109/IROS.2011.6094427}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/KormushevUCTC11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/automatica/MarkouP10, author = {Michael M. Markou and Christos G. Panayiotou}, title = {On-line control of the threshold policy parameter for multiclass systems}, journal = {Autom.}, volume = {46}, number = {3}, pages = {528--536}, year = {2010}, url = {https://doi.org/10.1016/j.automatica.2009.12.002}, doi = {10.1016/J.AUTOMATICA.2009.12.002}, timestamp = {Thu, 20 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/automatica/MarkouP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/SehnkeORGPS10, author = {Frank Sehnke and Christian Osendorfer and Thomas R{\"{u}}ckstie{\ss} and Alex Graves and Jan Peters and J{\"{u}}rgen Schmidhuber}, title = {Parameter-exploring policy gradients}, journal = {Neural Networks}, volume = {23}, number = {4}, pages = {551--559}, year = {2010}, url = {https://doi.org/10.1016/j.neunet.2009.12.004}, doi = {10.1016/J.NEUNET.2009.12.004}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/nn/SehnkeORGPS10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icann/GruttnerSSS10, author = {Mandy Gr{\"{u}}ttner and Frank Sehnke and Tom Schaul and J{\"{u}}rgen Schmidhuber}, editor = {Konstantinos I. Diamantaras and Wlodek Duch and Lazaros S. Iliadis}, title = {Multi-Dimensional Deep Memory Atari-Go Players for Parameter Exploring Policy Gradients}, booktitle = {Artificial Neural Networks - {ICANN} 2010, 20th International Conference, Thessaloniki, Greece, September 15-18, 2010, Proceedings, Part {II}}, series = {Lecture Notes in Computer Science}, volume = {6353}, pages = {114--123}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-15822-3\_14}, doi = {10.1007/978-3-642-15822-3\_14}, timestamp = {Tue, 14 May 2019 10:00:49 +0200}, biburl = {https://dblp.org/rec/conf/icann/GruttnerSSS10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icmla/SehnkeGOS10, author = {Frank Sehnke and Alex Graves and Christian Osendorfer and J{\"{u}}rgen Schmidhuber}, editor = {Sorin Draghici and Taghi M. Khoshgoftaar and Vasile Palade and Witold Pedrycz and M. Arif Wani and Xingquan Zhu}, title = {Multimodal Parameter-exploring Policy Gradients}, booktitle = {The Ninth International Conference on Machine Learning and Applications, {ICMLA} 2010, Washington, DC, USA, 12-14 December 2010}, pages = {113--118}, publisher = {{IEEE} Computer Society}, year = {2010}, url = {https://doi.org/10.1109/ICMLA.2010.24}, doi = {10.1109/ICMLA.2010.24}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icmla/SehnkeGOS10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/MiyamaeNOK10, author = {Atsushi Miyamae and Yuichi Nagata and Isao Ono and Shigenobu Kobayashi}, editor = {John D. Lafferty and Christopher K. I. Williams and John Shawe{-}Taylor and Richard S. Zemel and Aron Culotta}, title = {Natural Policy Gradient Methods with Parameter-based Exploration for Control Tasks}, booktitle = {Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, Vancouver, British Columbia, Canada}, pages = {1660--1668}, publisher = {Curran Associates, Inc.}, year = {2010}, url = {https://proceedings.neurips.cc/paper/2010/hash/44c4c17332cace2124a1a836d9fc4b6f-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/MiyamaeNOK10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/questa/CilOK09, author = {Eren Basar {\c{C}}il and E. Lerzan {\"{O}}rmeci and Fikri Karaesmen}, title = {Effects of system parameters on the optimal policy structure in a class of queueing control problems}, journal = {Queueing Syst. Theory Appl.}, volume = {61}, number = {4}, pages = {273--304}, year = {2009}, url = {https://doi.org/10.1007/s11134-009-9109-x}, doi = {10.1007/S11134-009-9109-X}, timestamp = {Tue, 01 Jun 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/questa/CilOK09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/candie/LauXZ08, author = {R. S. M. Lau and Jinxing Xie and Xiande Zhao}, title = {Effects of inventory policy on supply chain performance: {A} simulation study of critical decision parameters}, journal = {Comput. Ind. Eng.}, volume = {55}, number = {3}, pages = {620--633}, year = {2008}, url = {https://doi.org/10.1016/j.cie.2008.02.002}, doi = {10.1016/J.CIE.2008.02.002}, timestamp = {Thu, 20 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/candie/LauXZ08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icann/SehnkeORGPS08, author = {Frank Sehnke and Christian Osendorfer and Thomas R{\"{u}}ckstie{\ss} and Alex Graves and Jan Peters and J{\"{u}}rgen Schmidhuber}, editor = {Vera Kurkov{\'{a}} and Roman Neruda and Jan Koutn{\'{\i}}k}, title = {Policy Gradients with Parameter-Based Exploration for Control}, booktitle = {Artificial Neural Networks - {ICANN} 2008 , 18th International Conference, Prague, Czech Republic, September 3-6, 2008, Proceedings, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {5163}, pages = {387--396}, publisher = {Springer}, year = {2008}, url = {https://doi.org/10.1007/978-3-540-87536-9\_40}, doi = {10.1007/978-3-540-87536-9\_40}, timestamp = {Tue, 14 May 2019 10:00:49 +0200}, biburl = {https://dblp.org/rec/conf/icann/SehnkeORGPS08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icuimc/GuptaGG08, author = {Shyam K. Gupta and Vikram Goyal and Anand Gupta}, editor = {Won Kim and Hyung{-}Jin Choi}, title = {Precomputation of privacy policy parameters for auditing {SQL} queries}, booktitle = {Proceedings of the 2nd International Conference on Ubiquitous Information Management and Communication, {ICUIMC} 2008, Suwon, Korea, January 31 - February 01, 2008}, pages = {87--93}, publisher = {{ACM}}, year = {2008}, url = {https://doi.org/10.1145/1352793.1352812}, doi = {10.1145/1352793.1352812}, timestamp = {Fri, 23 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icuimc/GuptaGG08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jors/Garcia-FloresWB03, author = {Rodolfo Garc{\'{\i}}a{-}Flores and X. Z. Wang and Thomas F. Burgess}, title = {Tuning inventory policy parameters in a small chemical company}, journal = {J. Oper. Res. Soc.}, volume = {54}, number = {4}, pages = {350--361}, year = {2003}, url = {https://doi.org/10.1057/palgrave.jors.2601530}, doi = {10.1057/PALGRAVE.JORS.2601530}, timestamp = {Fri, 22 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jors/Garcia-FloresWB03.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/policy/BelokosztolszkiEM03, author = {Andr{\'{a}}s Belokosztolszki and David M. Eyers and Ken Moody}, title = {Policy Contexts: Controlling Information Flow in Parameterised {RBAC}}, booktitle = {4th {IEEE} International Workshop on Policies for Distributed Systems and Networks {(POLICY} 2003), 4-6 June 2003, Lake Como, Italy}, pages = {99--110}, publisher = {{IEEE} Computer Society}, year = {2003}, url = {https://doi.org/10.1109/POLICY.2003.1206964}, doi = {10.1109/POLICY.2003.1206964}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/policy/BelokosztolszkiEM03.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icc/AbdallahEE99, author = {Mohamed M. Abdallah and Mahmoud T. El{-}Hadidi and Khaled El{-}Sayed}, title = {Performance analysis and estimation of call admission policy parameters for multiple traffic classes in wireless {ATM} networks}, booktitle = {1999 {IEEE} International Conference on Communications: Global Convergence Through Communications, {ICC} 1999, Vancouver, BC, Canada, June 18-22, 1999}, pages = {404--410}, publisher = {{IEEE}}, year = {1999}, url = {https://doi.org/10.1109/ICC.1999.767972}, doi = {10.1109/ICC.1999.767972}, timestamp = {Mon, 23 Nov 2020 08:36:56 +0100}, biburl = {https://dblp.org/rec/conf/icc/AbdallahEE99.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscc/AbdallahEE99, author = {Mohamed M. Abdallah and Mahmoud T. El{-}Hadidi and Khaled M. F. Elsayed}, title = {Effect of User Mobility on the QoS Parameters for the Guard Channel Policy}, booktitle = {Proceedings of the Fourth {IEEE} Symposium on Computers and Communications {(ISCC} 1999), 6-8 July 1999, Sharm El Sheikh, Red Sea, Egypt}, pages = {409--415}, publisher = {{IEEE} Computer Society}, year = {1999}, url = {https://doi.org/10.1109/ISCC.1999.780933}, doi = {10.1109/ISCC.1999.780933}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iscc/AbdallahEE99.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/wcnc/AbdallahEE99, author = {Mohamed M. Abdallah and Khaled M. F. Elsayed and Mahmoud T. El{-}Hadidi}, title = {Effect of user mobility on the QoS parameters for the guard channel policy}, booktitle = {1999 {IEEE} Wireless Communications and Networking Conference, {WCNC} 1999, September 21-24, 1999, New Orleans, Louisiana, {USA}}, pages = {1503--1507}, publisher = {{IEEE}}, year = {1999}, url = {https://doi.org/10.1109/WCNC.1999.796989}, doi = {10.1109/WCNC.1999.796989}, timestamp = {Wed, 16 Oct 2019 14:14:50 +0200}, biburl = {https://dblp.org/rec/conf/wcnc/AbdallahEE99.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/mmor/Eijs94, author = {Marc J. G. van Eijs}, title = {On the determination of the control parameters of the optimal can-order policy}, journal = {Math. Methods Oper. Res.}, volume = {39}, number = {3}, pages = {289--304}, year = {1994}, url = {https://doi.org/10.1007/BF01435459}, doi = {10.1007/BF01435459}, timestamp = {Tue, 03 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/mmor/Eijs94.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.