Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Shangtong Zhang
@article{DBLP:journals/corr/abs-2401-07844,
author = {Shuze Liu and
Shuhang Chen and
Shangtong Zhang},
title = {The {ODE} Method for Stochastic Approximation and Reinforcement Learning
with Markovian Noise},
journal = {CoRR},
volume = {abs/2401.07844},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.07844},
doi = {10.48550/ARXIV.2401.07844},
eprinttype = {arXiv},
eprint = {2401.07844},
timestamp = {Thu, 01 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-07844.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcad/WeiWZYJWQZ23,
author = {Yuntao Wei and
Xueyan Wang and
Shangtong Zhang and
Jianlei Yang and
Xiaotao Jia and
Zhaohao Wang and
Gang Qu and
Weisheng Zhao},
title = {{IMGA:} Efficient In-Memory Graph Convolution Network Aggregation
With Data Flow Optimizations},
journal = {{IEEE} Trans. Comput. Aided Des. Integr. Circuits Syst.},
volume = {42},
number = {12},
pages = {4695--4705},
year = {2023},
url = {https://doi.org/10.1109/TCAD.2023.3288509},
doi = {10.1109/TCAD.2023.3288509},
timestamp = {Sun, 10 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tcad/WeiWZYJWQZ23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/Zhang23c,
author = {Shangtong Zhang},
editor = {Brian Williams and
Yiling Chen and
Jennifer Neville},
title = {A New Challenge in Policy Evaluation},
booktitle = {Thirty-Seventh {AAAI} Conference on Artificial Intelligence, {AAAI}
2023, Thirty-Fifth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2023, Thirteenth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2023, Washington, DC, USA, February
7-14, 2023},
pages = {15465},
publisher = {{AAAI} Press},
year = {2023},
url = {https://doi.org/10.1609/aaai.v37i13.26832},
doi = {10.1609/AAAI.V37I13.26832},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/Zhang23c.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ZhangCL23,
author = {Shangtong Zhang and
Remi Tachet des Combes and
Romain Laroche},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {On the Convergence of {SARSA} with Linear Function Approximation},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {41613--41646},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/zhang23al.html},
timestamp = {Mon, 28 Aug 2023 17:23:08 +0200},
biburl = {https://dblp.org/rec/conf/icml/ZhangCL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-13734,
author = {Shuze Liu and
Shangtong Zhang},
title = {Improving Monte Carlo Evaluation with Offline Data},
journal = {CoRR},
volume = {abs/2301.13734},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.13734},
doi = {10.48550/ARXIV.2301.13734},
eprinttype = {arXiv},
eprint = {2301.13734},
timestamp = {Thu, 02 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-13734.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-01170,
author = {Xiaochi Qian and
Shangtong Zhang},
title = {Direct Gradient Temporal Difference Learning},
journal = {CoRR},
volume = {abs/2308.01170},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.01170},
doi = {10.48550/ARXIV.2308.01170},
eprinttype = {arXiv},
eprint = {2308.01170},
timestamp = {Mon, 21 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-01170.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-03526,
author = {Micha{\"{e}}l Mathieu and
Sherjil Ozair and
Srivatsan Srinivasan and
{\c{C}}aglar G{\"{u}}l{\c{c}}ehre and
Shangtong Zhang and
Ray Jiang and
Tom Le Paine and
Richard Powell and
Konrad Zolna and
Julian Schrittwieser and
David H. Choi and
Petko Georgiev and
Daniel Toyama and
Aja Huang and
Roman Ring and
Igor Babuschkin and
Timo Ewalds and
Mahyar Bordbar and
Sarah Henderson and
Sergio G{\'{o}}mez Colmenarejo and
A{\"{a}}ron van den Oord and
Wojciech Marian Czarnecki and
Nando de Freitas and
Oriol Vinyals},
title = {AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning},
journal = {CoRR},
volume = {abs/2308.03526},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.03526},
doi = {10.48550/ARXIV.2308.03526},
eprinttype = {arXiv},
eprint = {2308.03526},
timestamp = {Tue, 22 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-03526.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/ZhangW22,
author = {Shangtong Zhang and
Shimon Whiteson},
title = {Truncated Emphatic Temporal Difference Methods for Prediction and
Control},
journal = {J. Mach. Learn. Res.},
volume = {23},
pages = {153:1--153:59},
year = {2022},
url = {http://jmlr.org/papers/v23/21-0934.html},
timestamp = {Wed, 07 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/ZhangW22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/ZhangCL22,
author = {Shangtong Zhang and
Remi Tachet des Combes and
Romain Laroche},
title = {Global Optimality and Finite Sample Analysis of Softmax Off-Policy
Actor Critic under State Distribution Mismatch},
journal = {J. Mach. Learn. Res.},
volume = {23},
pages = {343:1--343:91},
year = {2022},
url = {http://jmlr.org/papers/v23/21-1306.html},
timestamp = {Wed, 07 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/ZhangCL22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/JiangZC0H22,
author = {Ray Jiang and
Shangtong Zhang and
Veronica Chelu and
Adam White and
Hado van Hasselt},
title = {Learning Expected Emphatic Traces for Deep {RL}},
booktitle = {Thirty-Sixth {AAAI} Conference on Artificial Intelligence, {AAAI}
2022, Thirty-Fourth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2022, The Twelveth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2022 Virtual Event, February 22
- March 1, 2022},
pages = {7015--7023},
publisher = {{AAAI} Press},
year = {2022},
url = {https://doi.org/10.1609/aaai.v36i6.20660},
doi = {10.1609/AAAI.V36I6.20660},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/JiangZC0H22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/ZhangLSWC22,
author = {Shangtong Zhang and
Romain Laroche and
Harm van Seijen and
Shimon Whiteson and
Remi Tachet des Combes},
editor = {Piotr Faliszewski and
Viviana Mascardi and
Catherine Pelachaud and
Matthew E. Taylor},
title = {A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms},
booktitle = {21st International Conference on Autonomous Agents and Multiagent
Systems, {AAMAS} 2022, Auckland, New Zealand, May 9-13, 2022},
pages = {1491--1499},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems
{(IFAAMAS)}},
year = {2022},
url = {https://www.ifaamas.org/Proceedings/aamas2022/pdfs/p1491.pdf},
doi = {10.5555/3535850.3536016},
timestamp = {Mon, 18 Jul 2022 17:13:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/ZhangLSWC22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-06828,
author = {Shangtong Zhang and
Remi Tachet des Combes and
Romain Laroche},
title = {On the Chattering of {SARSA} with Linear Function Approximation},
journal = {CoRR},
volume = {abs/2202.06828},
year = {2022},
url = {https://arxiv.org/abs/2202.06828},
eprinttype = {arXiv},
eprint = {2202.06828},
timestamp = {Fri, 18 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-06828.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ZhangLW21,
author = {Shangtong Zhang and
Bo Liu and
Shimon Whiteson},
title = {Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning},
booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI}
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9,
2021},
pages = {10905--10913},
publisher = {{AAAI} Press},
year = {2021},
url = {https://doi.org/10.1609/aaai.v35i12.17302},
doi = {10.1609/AAAI.V35I12.17302},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ZhangLW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ZhangWSW21,
author = {Shangtong Zhang and
Yi Wan and
Richard S. Sutton and
Shimon Whiteson},
editor = {Marina Meila and
Tong Zhang},
title = {Average-Reward Off-Policy Policy Evaluation with Function Approximation},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {12578--12588},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/zhang21u.html},
timestamp = {Thu, 14 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/ZhangWSW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ZhangYW21,
author = {Shangtong Zhang and
Hengshuai Yao and
Shimon Whiteson},
editor = {Marina Meila and
Tong Zhang},
title = {Breaking the Deadly Triad with a Target Network},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {12621--12631},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/zhang21y.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/ZhangYW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/ZhangBW21,
author = {Shangtong Zhang and
Wendelin Boehmer and
Shimon Whiteson},
editor = {Zhi{-}Hua Zhou},
title = {Deep Residual Reinforcement Learning (Extended Abstract)},
booktitle = {Proceedings of the Thirtieth International Joint Conference on Artificial
Intelligence, {IJCAI} 2021, Virtual Event / Montreal, Canada, 19-27
August 2021},
pages = {4869--4873},
publisher = {ijcai.org},
year = {2021},
url = {https://doi.org/10.24963/ijcai.2021/668},
doi = {10.24963/IJCAI.2021/668},
timestamp = {Wed, 25 Aug 2021 17:11:16 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/ZhangBW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-02808,
author = {Shangtong Zhang and
Yi Wan and
Richard S. Sutton and
Shimon Whiteson},
title = {Average-Reward Off-Policy Policy Evaluation with Function Approximation},
journal = {CoRR},
volume = {abs/2101.02808},
year = {2021},
url = {https://arxiv.org/abs/2101.02808},
eprinttype = {arXiv},
eprint = {2101.02808},
timestamp = {Thu, 14 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2101-02808.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-08862,
author = {Shangtong Zhang and
Hengshuai Yao and
Shimon Whiteson},
title = {Breaking the Deadly Triad with a Target Network},
journal = {CoRR},
volume = {abs/2101.08862},
year = {2021},
url = {https://arxiv.org/abs/2101.08862},
eprinttype = {arXiv},
eprint = {2101.08862},
timestamp = {Sat, 30 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2101-08862.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-05405,
author = {Ray Jiang and
Shangtong Zhang and
Veronica Chelu and
Adam White and
Hado van Hasselt},
title = {Learning Expected Emphatic Traces for Deep {RL}},
journal = {CoRR},
volume = {abs/2107.05405},
year = {2021},
url = {https://arxiv.org/abs/2107.05405},
eprinttype = {arXiv},
eprint = {2107.05405},
timestamp = {Mon, 25 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-05405.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-05338,
author = {Shangtong Zhang and
Shimon Whiteson},
title = {Truncated Emphatic Temporal Difference Methods for Prediction and
Control},
journal = {CoRR},
volume = {abs/2108.05338},
year = {2021},
url = {https://arxiv.org/abs/2108.05338},
eprinttype = {arXiv},
eprint = {2108.05338},
timestamp = {Wed, 18 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2108-05338.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-02997,
author = {Shangtong Zhang and
Remi Tachet des Combes and
Romain Laroche},
title = {Global Optimality and Finite Sample Analysis of Softmax Off-Policy
Actor Critic under State Distribution Mismatch},
journal = {CoRR},
volume = {abs/2111.02997},
year = {2021},
url = {https://arxiv.org/abs/2111.02997},
eprinttype = {arXiv},
eprint = {2111.02997},
timestamp = {Fri, 05 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-02997.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/0001WLXZWX20,
author = {Yuhang Song and
Jianyi Wang and
Thomas Lukasiewicz and
Zhenghua Xu and
Shangtong Zhang and
Andrzej Wojcicki and
Mai Xu},
title = {Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards},
booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI}
2020, The Thirty-Second Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA,
February 7-12, 2020},
pages = {5826--5833},
publisher = {{AAAI} Press},
year = {2020},
url = {https://doi.org/10.1609/aaai.v34i04.6040},
doi = {10.1609/AAAI.V34I04.6040},
timestamp = {Fri, 08 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/0001WLXZWX20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/ZhangBW20,
author = {Shangtong Zhang and
Wendelin Boehmer and
Shimon Whiteson},
editor = {Amal El Fallah Seghrouchni and
Gita Sukthankar and
Bo An and
Neil Yorke{-}Smith},
title = {Deep Residual Reinforcement Learning},
booktitle = {Proceedings of the 19th International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} '20, Auckland, New Zealand, May 9-13,
2020},
pages = {1611--1619},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
year = {2020},
url = {https://dl.acm.org/doi/10.5555/3398761.3398946},
doi = {10.5555/3398761.3398946},
timestamp = {Tue, 26 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/ZhangBW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ZhangLW20,
author = {Shangtong Zhang and
Bo Liu and
Shimon Whiteson},
title = {GradientDICE: Rethinking Generalized Offline Estimation of Stationary
Values},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {11194--11203},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/zhang20r.html},
timestamp = {Tue, 07 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/ZhangLW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ZhangLYW20,
author = {Shangtong Zhang and
Bo Liu and
Hengshuai Yao and
Shimon Whiteson},
title = {Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function
Approximation},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {11204--11213},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/zhang20s.html},
timestamp = {Tue, 07 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/ZhangLYW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZhangVW20,
author = {Shangtong Zhang and
Vivek Veeriah and
Shimon Whiteson},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Learning Retrospective Knowledge with Reverse Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/e6cbc650cd5798a05dfd0f51d14cde5c-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/ZhangVW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2001-11113,
author = {Shangtong Zhang and
Bo Liu and
Shimon Whiteson},
title = {GradientDICE: Rethinking Generalized Offline Estimation of Stationary
Values},
journal = {CoRR},
volume = {abs/2001.11113},
year = {2020},
url = {https://arxiv.org/abs/2001.11113},
eprinttype = {arXiv},
eprint = {2001.11113},
timestamp = {Tue, 07 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2001-11113.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2004-10888,
author = {Shangtong Zhang and
Bo Liu and
Shimon Whiteson},
title = {Per-Step Reward: {A} New Perspective for Risk-Averse Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2004.10888},
year = {2020},
url = {https://arxiv.org/abs/2004.10888},
eprinttype = {arXiv},
eprint = {2004.10888},
timestamp = {Tue, 07 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2004-10888.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-06703,
author = {Shangtong Zhang and
Vivek Veeriah and
Shimon Whiteson},
title = {Learning Retrospective Knowledge with Reverse Reinforcement Learning},
journal = {CoRR},
volume = {abs/2007.06703},
year = {2020},
url = {https://arxiv.org/abs/2007.06703},
eprinttype = {arXiv},
eprint = {2007.06703},
timestamp = {Tue, 21 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-06703.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-01069,
author = {Shangtong Zhang and
Romain Laroche and
Harm van Seijen and
Shimon Whiteson and
Remi Tachet des Combes},
title = {A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms},
journal = {CoRR},
volume = {abs/2010.01069},
year = {2020},
url = {https://arxiv.org/abs/2010.01069},
eprinttype = {arXiv},
eprint = {2010.01069},
timestamp = {Mon, 12 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-01069.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ZhangY19,
author = {Shangtong Zhang and
Hengshuai Yao},
title = {{ACE:} An Actor Ensemble Algorithm for Continuous Control with Tree
Search},
booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI}
2019, The Thirty-First Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii,
USA, January 27 - February 1, 2019},
pages = {5789--5796},
publisher = {{AAAI} Press},
year = {2019},
url = {https://doi.org/10.1609/aaai.v33i01.33015789},
doi = {10.1609/AAAI.V33I01.33015789},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ZhangY19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ZhangY19a,
author = {Shangtong Zhang and
Hengshuai Yao},
title = {{QUOTA:} The Quantile Option Architecture for Reinforcement Learning},
booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI}
2019, The Thirty-First Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii,
USA, January 27 - February 1, 2019},
pages = {5797--5804},
publisher = {{AAAI} Press},
year = {2019},
url = {https://doi.org/10.1609/aaai.v33i01.33015797},
doi = {10.1609/AAAI.V33I01.33015797},
timestamp = {Tue, 02 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aaai/ZhangY19a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/MavrinZYK19,
author = {Borislav Mavrin and
Shangtong Zhang and
Hengshuai Yao and
Linglong Kong},
editor = {Edith Elkind and
Manuela Veloso and
Noa Agmon and
Matthew E. Taylor},
title = {Exploration in the Face of Parametric and Intrinsic Uncertainties},
booktitle = {Proceedings of the 18th International Conference on Autonomous Agents
and MultiAgent Systems, {AAMAS} '19, Montreal, QC, Canada, May 13-17,
2019},
pages = {2117--2119},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
year = {2019},
url = {http://dl.acm.org/citation.cfm?id=3332029},
timestamp = {Wed, 29 May 2019 16:36:58 +0200},
biburl = {https://dblp.org/rec/conf/atal/MavrinZYK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZhangBW19,
author = {Shangtong Zhang and
Wendelin Boehmer and
Shimon Whiteson},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Generalized Off-Policy Actor-Critic},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference
on Neural Information Processing Systems 2019, NeurIPS 2019, December
8-14, 2019, Vancouver, BC, Canada},
pages = {1999--2009},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/0e095e054ee94774d6a496099eb1cf6a-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/ZhangBW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZhangW19a,
author = {Shangtong Zhang and
Shimon Whiteson},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {{DAC:} The Double Actor-Critic Architecture for Learning Options},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference
on Neural Information Processing Systems 2019, NeurIPS 2019, December
8-14, 2019, Vancouver, BC, Canada},
pages = {2010--2020},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/4f284803bd0966cc24fa8683a34afc6e-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/ZhangW19a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1903-11329,
author = {Shangtong Zhang and
Wendelin Boehmer and
Shimon Whiteson},
title = {Generalized Off-Policy Actor-Critic},
journal = {CoRR},
volume = {abs/1903.11329},
year = {2019},
url = {http://arxiv.org/abs/1903.11329},
eprinttype = {arXiv},
eprint = {1903.11329},
timestamp = {Tue, 02 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1903-11329.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-12691,
author = {Shangtong Zhang and
Shimon Whiteson},
title = {{DAC:} The Double Actor-Critic Architecture for Learning Options},
journal = {CoRR},
volume = {abs/1904.12691},
year = {2019},
url = {http://arxiv.org/abs/1904.12691},
eprinttype = {arXiv},
eprint = {1904.12691},
timestamp = {Thu, 02 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-12691.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-01072,
author = {Shangtong Zhang and
Wendelin Boehmer and
Shimon Whiteson},
title = {Deep Residual Reinforcement Learning},
journal = {CoRR},
volume = {abs/1905.01072},
year = {2019},
url = {http://arxiv.org/abs/1905.01072},
eprinttype = {arXiv},
eprint = {1905.01072},
timestamp = {Mon, 27 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-01072.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-04640,
author = {Yuhang Song and
Jianyi Wang and
Thomas Lukasiewicz and
Zhenghua Xu and
Shangtong Zhang and
Mai Xu},
title = {Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards},
journal = {CoRR},
volume = {abs/1905.04640},
year = {2019},
url = {http://arxiv.org/abs/1905.04640},
eprinttype = {arXiv},
eprint = {1905.04640},
timestamp = {Wed, 20 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-04640.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-06125,
author = {Borislav Mavrin and
Shangtong Zhang and
Hengshuai Yao and
Linglong Kong and
Kaiwen Wu and
Yaoliang Yu},
title = {Distributional Reinforcement Learning for Efficient Exploration},
journal = {CoRR},
volume = {abs/1905.06125},
year = {2019},
url = {http://arxiv.org/abs/1905.06125},
eprinttype = {arXiv},
eprint = {1905.06125},
timestamp = {Tue, 28 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-06125.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-04384,
author = {Shangtong Zhang and
Bo Liu and
Hengshuai Yao and
Shimon Whiteson},
title = {Provably Convergent Off-Policy Actor-Critic with Function Approximation},
journal = {CoRR},
volume = {abs/1911.04384},
year = {2019},
url = {http://arxiv.org/abs/1911.04384},
eprinttype = {arXiv},
eprint = {1911.04384},
timestamp = {Tue, 07 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-04384.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jossw/CurtinELMGZ18,
author = {Ryan R. Curtin and
Marcus Edel and
Mikhail Lozhnikov and
Yannis Mentekidis and
Sumedh Ghaisas and
Shangtong Zhang},
title = {mlpack 3: a fast, flexible machine learning library},
journal = {J. Open Source Softw.},
volume = {3},
number = {26},
pages = {726},
year = {2018},
url = {https://doi.org/10.21105/joss.00726},
doi = {10.21105/JOSS.00726},
timestamp = {Tue, 16 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jossw/CurtinELMGZ18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-02073,
author = {Shangtong Zhang and
Borislav Mavrin and
Linglong Kong and
Bo Liu and
Hengshuai Yao},
title = {{QUOTA:} The Quantile Option Architecture for Reinforcement Learning},
journal = {CoRR},
volume = {abs/1811.02073},
year = {2018},
url = {http://arxiv.org/abs/1811.02073},
eprinttype = {arXiv},
eprint = {1811.02073},
timestamp = {Tue, 07 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-02073.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-02696,
author = {Shangtong Zhang and
Hao Chen and
Hengshuai Yao},
title = {{ACE:} An Actor Ensemble Algorithm for Continuous Control with Tree
Search},
journal = {CoRR},
volume = {abs/1811.02696},
year = {2018},
url = {http://arxiv.org/abs/1811.02696},
eprinttype = {arXiv},
eprint = {1811.02696},
timestamp = {Thu, 22 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-02696.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pkdd/VeeriahZS17,
author = {Vivek Veeriah and
Shangtong Zhang and
Richard S. Sutton},
editor = {Michelangelo Ceci and
Jaakko Hollm{\'{e}}n and
Ljupco Todorovski and
Celine Vens and
Saso Dzeroski},
title = {Crossprop: Learning Representations by Stochastic Meta-Gradient Descent
in Neural Networks},
booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference,
{ECML} {PKDD} 2017, Skopje, Macedonia, September 18-22, 2017, Proceedings,
Part {I}},
series = {Lecture Notes in Computer Science},
volume = {10534},
pages = {445--459},
publisher = {Springer},
year = {2017},
url = {https://doi.org/10.1007/978-3-319-71249-9\_27},
doi = {10.1007/978-3-319-71249-9\_27},
timestamp = {Tue, 14 May 2019 10:00:47 +0200},
biburl = {https://dblp.org/rec/conf/pkdd/VeeriahZS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1712-00006,
author = {Shangtong Zhang and
Osmar R. Za{\"{\i}}ane},
title = {Comparing Deep Reinforcement Learning and Evolutionary Methods in
Continuous Control},
journal = {CoRR},
volume = {abs/1712.00006},
year = {2017},
url = {http://arxiv.org/abs/1712.00006},
eprinttype = {arXiv},
eprint = {1712.00006},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1712-00006.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1712-01275,
author = {Shangtong Zhang and
Richard S. Sutton},
title = {A Deeper Look at Experience Replay},
journal = {CoRR},
volume = {abs/1712.01275},
year = {2017},
url = {http://arxiv.org/abs/1712.01275},
eprinttype = {arXiv},
eprint = {1712.01275},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1712-01275.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mir/ZhangZZLQHZW15,
author = {Pengjing Zhang and
Xiaoqing Zheng and
Wenqiang Zhang and
Siyan Li and
Sheng Qian and
Wenqi He and
Shangtong Zhang and
Ziyuan Wang},
editor = {Alexander G. Hauptmann and
Chong{-}Wah Ngo and
Xiangyang Xue and
Yu{-}Gang Jiang and
Cees Snoek and
Nuno Vasconcelos},
title = {A Deep Neural Network for Modeling Music},
booktitle = {Proceedings of the 5th {ACM} on International Conference on Multimedia
Retrieval, Shanghai, China, June 23-26, 2015},
pages = {379--386},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2671188.2749367},
doi = {10.1145/2671188.2749367},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/mir/ZhangZZLQHZW15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
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.
last updated on 2024-03-16 00:56 CET 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:
