Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDSearch dblp for Publications
export results for "policy parameter"
download as .bib file
@article{DBLP:journals/eswa/KwongSLYCK24,
author = {Chiew Foong Kwong and
Chenhao Shi and
Qianyu Liu and
Sen Yang and
David Chieng and
Pushpendu Kar},
title = {Autonomous handover parameter optimisation for 5G cellular networks
using deep deterministic policy gradient},
journal = {Expert Syst. Appl.},
volume = {246},
pages = {122871},
year = {2024}
}
@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}
}
@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}
}
@inproceedings{DBLP:conf/aaaiss/NuppnauKR24,
author = {Mark Nuppnau and
Khalid Kattan and
Robert G. Reynolds},
title = {Cultural Algorithm Guided Policy Gradient with Parameter Exploration},
booktitle = {{AAAI} Spring Symposia},
pages = {380--386},
publisher = {{AAAI} Press},
year = {2024}
}
@inproceedings{DBLP:conf/aistats/MondalA24,
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},
booktitle = {{AISTATS}},
series = {Proceedings of Machine Learning Research},
volume = {238},
pages = {3097--3105},
publisher = {{PMLR}},
year = {2024}
}
@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}
}
@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}
}
@article{DBLP:journals/corr/abs-2405-21043,
author = {Fengdi Che and
Chenjun Xiao and
Jincheng Mei and
Bo Dai and
Ramki Gummadi and
Oscar A Ramirez and
Christopher K. Harris and
A. Rupam Mahmood and
Dale Schuurmans},
title = {Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping
with Function Approximation},
journal = {CoRR},
volume = {abs/2405.21043},
year = {2024}
}
@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}
}
@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}
}
@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}
}
@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}
}
@inproceedings{DBLP:conf/aistats/PattathilZO23,
author = {Sarath Pattathil and
Kaiqing Zhang and
Asuman E. Ozdaglar},
title = {Symmetric (Optimistic) Natural Policy Gradient for Multi-Agent Learning
with Parameter Convergence},
booktitle = {{AISTATS}},
series = {Proceedings of Machine Learning Research},
volume = {206},
pages = {5641--5685},
publisher = {{PMLR}},
year = {2023}
}
@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 = {{ICLR}},
publisher = {OpenReview.net},
year = {2023}
}
@inproceedings{DBLP:conf/nips/AlfanoYR23,
author = {Carlo Alfano and
Rui Yuan and
Patrick Rebeschini},
title = {A Novel Framework for Policy Mirror Descent with General Parameterization
and Linear Convergence},
booktitle = {NeurIPS},
year = {2023}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@inproceedings{DBLP:conf/cdc/SunF21,
author = {Yue Sun and
Maryam Fazel},
title = {Learning Optimal Controllers by Policy Gradient: Global Optimality
via Convex Parameterization},
booktitle = {{CDC}},
pages = {4576--4581},
publisher = {{IEEE}},
year = {2021}
}
@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}},
pages = {1--6},
publisher = {{IEEE}},
year = {2021}
}
@inproceedings{DBLP:conf/ijcci/GomezT21,
author = {Alejandro de Miguel Gomez and
Farshad Ghassemi Toosi},
title = {Continuous Parameter Control in Genetic Algorithms using Policy Gradient
Reinforcement Learning},
booktitle = {{IJCCI}},
pages = {115--122},
publisher = {{SCITEPRESS}},
year = {2021}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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 = {{FUZZ-IEEE}},
pages = {1--8},
publisher = {{IEEE}},
year = {2020}
}
@inproceedings{DBLP:conf/ijcnn/Hosino20,
author = {Tikara Hosino},
title = {Variational Bayesian Parameter-Based Policy Exploration},
booktitle = {{IJCNN}},
pages = {1--7},
publisher = {{IEEE}},
year = {2020}
}
@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 = {{IROS}},
pages = {5445--5452},
publisher = {{IEEE}},
year = {2020}
}
@inproceedings{DBLP:conf/wpes/SomeR20,
author = {Doli{\`{e}}re Francis Som{\'{e}} and
Tamara Rezk},
title = {Strenghtening Content Security Policy via Monitoring and {URL} Parameters
Filtering},
booktitle = {WPES@CCS},
pages = {1--13},
publisher = {{ACM}},
year = {2020}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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 = {{CCTA}},
pages = {320--324},
publisher = {{IEEE}},
year = {2019}
}
@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 = {{ICRA}},
pages = {2831--2837},
publisher = {{IEEE}},
year = {2019}
}
@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 = {{ICTC}},
pages = {1324--1326},
publisher = {{IEEE}},
year = {2019}
}
@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 = {{RO-MAN}},
pages = {1--6},
publisher = {{IEEE}},
year = {2019}
}
@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}
}
@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}
}
@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}
}
@inproceedings{DBLP:conf/ccgrid/ChunduriGLSN18,
author = {Sudheer Chunduri and
Meysam Ghaffari and
Mehran Sadeghi Lahijani and
Ashok Srinivasan and
Sirish Namilae},
title = {Parallel Low Discrepancy Parameter Sweep for Public Health Policy},
booktitle = {CCGrid},
pages = {291--300},
publisher = {{IEEE} Computer Society},
year = {2018}
}
@inproceedings{DBLP:conf/gecco/OhashiFSA18,
author = {Kyotaro Ohashi and
Natsuki Fujiyoshi and
Naoki Sakamoto and
Youhei Akimoto},
title = {Model parameter adaptive instance-based policy optimization for episodic
control tasks of nonholonomic systems},
booktitle = {{GECCO} (Companion)},
pages = {1426--1433},
publisher = {{ACM}},
year = {2018}
}
@inproceedings{DBLP:conf/iccsip/GaoWLSH18,
author = {Xiang Gao and
Yue Wen and
Minhan Li and
Jennie Si and
He (Helen) Huang},
title = {Robotic Knee Parameter Tuning Using Approximate Policy Iteration},
booktitle = {{ICCSIP} {(1)}},
series = {Communications in Computer and Information Science},
volume = {1005},
pages = {554--563},
publisher = {Springer},
year = {2018}
}
@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 = {{ICRA}},
pages = {1--9},
publisher = {{IEEE}},
year = {2018}
}
@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 = {{IROS}},
pages = {6445--6452},
publisher = {{IEEE}},
year = {2018}
}
@inproceedings{DBLP:conf/safecomp/BehzadanM18,
author = {Vahid Behzadan and
Arslan Munir},
title = {Mitigation of Policy Manipulation Attacks on Deep Q-Networks with
Parameter-Space Noise},
booktitle = {{SAFECOMP} Workshops},
series = {Lecture Notes in Computer Science},
volume = {11094},
pages = {406--417},
publisher = {Springer},
year = {2018}
}
@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}
}
@inproceedings{DBLP:conf/ant/ValmassoiGSSP17,
author = {Arianna Valmassoi and
Salem Gharbia and
Santa Stibe and
Silvana Di Sabatino and
Francesco Pilla},
title = {Future Impacts of the Reforestation Policy on the amospheric parameters:
a sensitivity study over Ireland},
booktitle = {{ANT/SEIT}},
series = {Procedia Computer Science},
volume = {109},
pages = {367--375},
publisher = {Elsevier},
year = {2017}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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}
}
@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 = {{ICARSC}},
pages = {17--22},
publisher = {{IEEE}},
year = {2015}
}
@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 = {{IJCNN}},
pages = {1--8},
publisher = {{IEEE}},
year = {2015}
}
@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 = {{SSCI}},
pages = {556--563},
publisher = {{IEEE}},
year = {2015}
}
@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}
}
@inproceedings{DBLP:conf/iros/ReinhartS14,
author = {Ren{\'{e}} Felix Reinhart and
Jochen Jakob Steil},
title = {Efficient policy search with a parameterized skill memory},
booktitle = {{IROS}},
pages = {1400--1407},
publisher = {{IEEE}},
year = {2014}
}
@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}
}
@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}
}
@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}
}
@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 = {{IEEE} {CLOUD}},
pages = {67--74},
publisher = {{IEEE} Computer Society},
year = {2013}
}
@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 = {{APNOMS}},
pages = {1--6},
publisher = {{IEEE}},
year = {2013}
}
@inproceedings{DBLP:conf/ascc/XiaJ13,
author = {Li Xia and
Qing{-}Shan Jia},
title = {Policy iteration for parameterized Markov decision processes and its
application},
booktitle = {{ASCC}},
pages = {1--6},
publisher = {{IEEE}},
year = {2013}
}
@inproceedings{DBLP:conf/icann/Sehnke13,
author = {Frank Sehnke},
title = {Efficient Baseline-Free Sampling in Parameter Exploring Policy Gradients:
Super Symmetric {PGPE}},
booktitle = {{ICANN}},
series = {Lecture Notes in Computer Science},
volume = {8131},
pages = {130--137},
publisher = {Springer},
year = {2013}
}
@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}
}
@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}
}
@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}
}
@phdthesis{DBLP:phd/dnb/Sehnke12,
author = {Frank Sehnke},
title = {Parameter exploring policy gradients and their implications},
school = {Technical University Munich},
year = {2012}
}
@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}
}
@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}
}
@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 = {{SLT}},
pages = {1--6},
publisher = {{IEEE}},
year = {2012}
}
@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}
}
@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}
}
@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}},
pages = {151--155},
publisher = {{IEEE}},
year = {2011}
}
@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 = {{IROS}},
pages = {318--324},
publisher = {{IEEE}},
year = {2011}
}
@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}
}
@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}
}
@inproceedings{DBLP:conf/icann/GruttnerSSS10,
author = {Mandy Gr{\"{u}}ttner and
Frank Sehnke and
Tom Schaul and
J{\"{u}}rgen Schmidhuber},
title = {Multi-Dimensional Deep Memory Atari-Go Players for Parameter Exploring
Policy Gradients},
booktitle = {{ICANN} {(2)}},
series = {Lecture Notes in Computer Science},
volume = {6353},
pages = {114--123},
publisher = {Springer},
year = {2010}
}
@inproceedings{DBLP:conf/icmla/SehnkeGOS10,
author = {Frank Sehnke and
Alex Graves and
Christian Osendorfer and
J{\"{u}}rgen Schmidhuber},
title = {Multimodal Parameter-exploring Policy Gradients},
booktitle = {{ICMLA}},
pages = {113--118},
publisher = {{IEEE} Computer Society},
year = {2010}
}
@inproceedings{DBLP:conf/nips/MiyamaeNOK10,
author = {Atsushi Miyamae and
Yuichi Nagata and
Isao Ono and
Shigenobu Kobayashi},
title = {Natural Policy Gradient Methods with Parameter-based Exploration for
Control Tasks},
booktitle = {{NIPS}},
pages = {1660--1668},
publisher = {Curran Associates, Inc.},
year = {2010}
}
@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}
}
@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}
}
@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},
title = {Policy Gradients with Parameter-Based Exploration for Control},
booktitle = {{ICANN} {(1)}},
series = {Lecture Notes in Computer Science},
volume = {5163},
pages = {387--396},
publisher = {Springer},
year = {2008}
}
@inproceedings{DBLP:conf/icuimc/GuptaGG08,
author = {Shyam K. Gupta and
Vikram Goyal and
Anand Gupta},
title = {Precomputation of privacy policy parameters for auditing {SQL} queries},
booktitle = {{ICUIMC}},
pages = {87--93},
publisher = {{ACM}},
year = {2008}
}
@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}
}
@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 = {{POLICY}},
pages = {99--110},
publisher = {{IEEE} Computer Society},
year = {2003}
}
@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 = {{ICC}},
pages = {404--410},
publisher = {{IEEE}},
year = {1999}
}
@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 = {{ISCC}},
pages = {409--415},
publisher = {{IEEE} Computer Society},
year = {1999}
}
@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 = {{WCNC}},
pages = {1503--1507},
publisher = {{IEEE}},
year = {1999}
}
@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}
}
a service of 
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.
retrieved on 2024-06-25 11:24 CEST from data curated by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
