Zobrazeno 1 - 10
of 73
pro vyhledávání: '"Shimon Whiteson"'
Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning
Publikováno v:
AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS
Autonomous Agents and Multi-Agent Systems, 35(2)
Autonomous Agents and Multi-Agent Systems
Autonomous Agents and Multi-Agent Systems, 35(2)
Autonomous Agents and Multi-Agent Systems
Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::20f9a3ab96cb6b445ac49707b5438d78
http://livrepository.liverpool.ac.uk/3126938/1/Castellini2021_Article_AnalysingFactorizationsOfActio.pdf
http://livrepository.liverpool.ac.uk/3126938/1/Castellini2021_Article_AnalysingFactorizationsOfActio.pdf
Publikováno v:
IJCAI
We revisit residual algorithms in both model-free and model-based reinforcement learning settings. We propose the bidirectional target network technique to stabilize residual algorithms, yielding a residual version of DDPG that significantly outperfo
Autor:
Shimon Whiteson
Publikováno v:
Computer Vision ISBN: 9783030032432
Adaptive Representations for Reinforcement Learning ISBN: 9783642139314
Adaptive Representations for Reinforcement Learning ISBN: 9783642139314
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9f6591a4cfd97d3909d74ea4aee61db
https://doi.org/10.1007/978-3-030-63416-2_859
https://doi.org/10.1007/978-3-030-63416-2_859
We present a mean-variance policy iteration (MVPI) framework for risk-averse control in a discounted infinite horizon MDP optimizing the variance of a per-step reward random variable. MVPI enjoys great flexibility in that any policy evaluation method
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b5f66a4b80f37d185af1408b7a2dc359
http://arxiv.org/abs/2004.10888
http://arxiv.org/abs/2004.10888
Publikováno v:
Autonomous Agents and Multi-Agent Systems
Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems
Autonomous Agents and Multi-Agent Systems, 34(1)
AAMAS
Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems
Autonomous Agents and Multi-Agent Systems, 34(1)
AAMAS
Interactive reinforcement learning provides a way for agents to learn to solve tasks from evaluative feedback provided by a human user. Previous research showed that humans give copious feedback early in training but very sparsely thereafter. In this
Publikováno v:
Springer US
Autonomous Agents and Multi-Agent Systems, 32(1)
Autonomous Agents and Multi-Agent Systems, 32(1)
Learning from rewards generated by a human trainer observing an agent in action has been proven to be a powerful method for teaching autonomous agents to perform challenging tasks, especially for those non-technical users. Since the efficacy of this
Autor:
Diederik M. Roijers, Shimon Whiteson
Publikováno v:
Synthesis Lectures on Artificial Intelligence and Machine Learning ISBN: 9783031004483
Many real-world decision problems have multiple objectives. For example, when choosing a medical treatment plan, we want to maximize the efficacy of the treatment, but also minimize the side effects. These objectives typically conflict, e.g., we can
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c2e6a3d03ba27fcdc0cb82c0d1590ed8
https://ora.ox.ac.uk/objects/uuid:28a76830-11d6-4367-b94a-656964762788
https://ora.ox.ac.uk/objects/uuid:28a76830-11d6-4367-b94a-656964762788
Autor:
Edward Grefenstette, Nantas Nardelli, Jakob Foerster, Tim Rocktäschel, Shimon Whiteson, Jelena Luketina, Jacob Andreas, Gregory Farquhar
Publikováno v:
IJCAI
To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation learning for la
Autor:
Feryal Behbahani, Frans A. Oliehoek, Sudhanshu Kasewa, Xi Chen, Kyriacos Shiarlis, Ciprian Stirbu, Supratik Paul, João P. P. Gomes, João V. Messias, Vitaly Kurin, Shimon Whiteson
Publikováno v:
2019 International Conference on Robotics and Automation, ICRA 2019
ICRA
ICRA
Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical. It has succeeded in a wide range of problems but typically relies on manually generated demonstrations or specially deployed sens
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::254bd54b247c73baa6dae572c364aca8
https://ora.ox.ac.uk/objects/uuid:1595342a-5cc4-4bf2-a919-22684b414c7e
https://ora.ox.ac.uk/objects/uuid:1595342a-5cc4-4bf2-a919-22684b414c7e
Publikováno v:
18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019: Proceedings of the Eighteenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS)
18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019
Delft University of Technology
18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019
Delft University of Technology
Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cf17c296b9f61dcab0dcc20332e1f300
http://resolver.tudelft.nl/uuid:8ca4ef09-6fc8-47de-b2c9-bc33671854ca
http://resolver.tudelft.nl/uuid:8ca4ef09-6fc8-47de-b2c9-bc33671854ca