Stop the war!
Остановите войну!
for scientists:
default search action
BibTeX records: William Dabney
@article{DBLP:journals/jmlr/GeramifardDKDH15, author = {Alborz Geramifard and Christoph Dann and Robert H. Klein and William Dabney and Jonathan P. How}, title = {RLPy: a value-function-based reinforcement learning framework for education and research}, journal = {J. Mach. Learn. Res.}, volume = {16}, pages = {1573--1578}, year = {2015}, url = {https://dl.acm.org/doi/10.5555/2789272.2886799}, doi = {10.5555/2789272.2886799}, timestamp = {Thu, 02 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jmlr/GeramifardDKDH15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/DabneyT14, author = {William Dabney and Philip S. Thomas}, editor = {Carla E. Brodley and Peter Stone}, title = {Natural Temporal Difference Learning}, booktitle = {Proceedings of the Twenty-Eighth {AAAI} Conference on Artificial Intelligence, July 27 -31, 2014, Qu{\'{e}}bec City, Qu{\'{e}}bec, Canada}, pages = {1767--1773}, publisher = {{AAAI} Press}, year = {2014}, url = {https://doi.org/10.1609/aaai.v28i1.9018}, doi = {10.1609/AAAI.V28I1.9018}, timestamp = {Mon, 04 Sep 2023 15:06:24 +0200}, biburl = {https://dblp.org/rec/conf/aaai/DabneyT14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/MahadevanLTDGJG014, author = {Sridhar Mahadevan and Bo Liu and Philip S. Thomas and William Dabney and Stephen Giguere and Nicholas Jacek and Ian Gemp and Ji Liu}, title = {Proximal Reinforcement Learning: {A} New Theory of Sequential Decision Making in Primal-Dual Spaces}, journal = {CoRR}, volume = {abs/1405.6757}, year = {2014}, url = {http://arxiv.org/abs/1405.6757}, eprinttype = {arXiv}, eprint = {1405.6757}, timestamp = {Tue, 26 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/MahadevanLTDGJG014.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/ThomasDGM13, author = {Philip S. Thomas and William Dabney and Stephen Giguere and Sridhar Mahadevan}, editor = {Christopher J. C. Burges and L{\'{e}}on Bottou and Zoubin Ghahramani and Kilian Q. Weinberger}, title = {Projected Natural Actor-Critic}, booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States}, pages = {2337--2345}, year = {2013}, url = {https://proceedings.neurips.cc/paper/2013/hash/dd77279f7d325eec933f05b1672f6a1f-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/ThomasDGM13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/DabneyB12, author = {William Dabney and Andrew G. Barto}, editor = {J{\"{o}}rg Hoffmann and Bart Selman}, title = {Adaptive Step-Size for Online Temporal Difference Learning}, booktitle = {Proceedings of the Twenty-Sixth {AAAI} Conference on Artificial Intelligence, July 22-26, 2012, Toronto, Ontario, Canada}, pages = {872--878}, publisher = {{AAAI} Press}, year = {2012}, url = {https://doi.org/10.1609/aaai.v26i1.8313}, doi = {10.1609/AAAI.V26I1.8313}, timestamp = {Mon, 04 Sep 2023 15:56:47 +0200}, biburl = {https://dblp.org/rec/conf/aaai/DabneyB12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sigir/CartrightCDDGKWYAMS12, author = {Marc{-}Allen Cartright and Ethem F. Can and William Dabney and Jeff Dalton and Logan Giorda and Kriste Krstovski and Xiaoye Wu and Ismet Zeki Yalniz and James Allan and R. Manmatha and David A. Smith}, editor = {William R. Hersh and Jamie Callan and Yoelle Maarek and Mark Sanderson}, title = {A framework for manipulating and searching multiple retrieval types}, booktitle = {The 35th International {ACM} {SIGIR} conference on research and development in Information Retrieval, {SIGIR} '12, Portland, OR, USA, August 12-16, 2012}, pages = {1001}, publisher = {{ACM}}, year = {2012}, url = {https://doi.org/10.1145/2348283.2348426}, doi = {10.1145/2348283.2348426}, timestamp = {Wed, 14 Nov 2018 10:58:10 +0100}, biburl = {https://dblp.org/rec/conf/sigir/CartrightCDDGKWYAMS12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcai/DabneyM07, author = {William Dabney and Amy McGovern}, editor = {Manuela M. Veloso}, title = {Utile Distinctions for Relational Reinforcement Learning}, booktitle = {{IJCAI} 2007, Proceedings of the 20th International Joint Conference on Artificial Intelligence, Hyderabad, India, January 6-12, 2007}, pages = {738--743}, year = {2007}, url = {http://ijcai.org/Proceedings/07/Papers/118.pdf}, timestamp = {Tue, 20 Aug 2019 16:17:11 +0200}, biburl = {https://dblp.org/rec/conf/ijcai/DabneyM07.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.