Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Slumbers, Oliver"'
Autor:
Schäfer, Lukas, Slumbers, Oliver, McAleer, Stephen, Du, Yali, Albrecht, Stefano V., Mguni, David
Existing value-based algorithms for cooperative multi-agent reinforcement learning (MARL) commonly rely on random exploration, such as $\epsilon$-greedy, to explore the environment. However, such exploration is inefficient at finding effective joint
Externí odkaz:
http://arxiv.org/abs/2302.03439
Autor:
Mguni, David, Sootla, Aivar, Ziomek, Juliusz, Slumbers, Oliver, Dai, Zipeng, Shao, Kun, Wang, Jun
Many real-world settings involve costs for performing actions; transaction costs in financial systems and fuel costs being common examples. In these settings, performing actions at each time step quickly accumulates costs leading to vastly suboptimal
Externí odkaz:
http://arxiv.org/abs/2205.15953
Autor:
Slumbers, Oliver, Mguni, David Henry, McAleer, Stephen Marcus, Blumberg, Stefano B., Wang, Jun, Yang, Yaodong
In order for agents in multi-agent systems (MAS) to be safe, they need to take into account the risks posed by the actions of other agents. However, the dominant paradigm in game theory (GT) assumes that agents are not affected by risk from other age
Externí odkaz:
http://arxiv.org/abs/2205.15434
Autor:
Mguni, David Henry, Jafferjee, Taher, Wang, Jianhong, Slumbers, Oliver, Perez-Nieves, Nicolas, Tong, Feifei, Yang, Li, Zhu, Jiangcheng, Yang, Yaodong, Wang, Jun
Efficient exploration is important for reinforcement learners to achieve high rewards. In multi-agent systems, coordinated exploration and behaviour is critical for agents to jointly achieve optimal outcomes. In this paper, we introduce a new general
Externí odkaz:
http://arxiv.org/abs/2112.02618
Autor:
Wang, Chenguang, Yang, Yaodong, Slumbers, Oliver, Han, Congying, Guo, Tiande, Zhang, Haifeng, Wang, Jun
In this paper, we introduce a two-player zero-sum framework between a trainable \emph{Solver} and a \emph{Data Generator} to improve the generalization ability of deep learning-based solvers for Traveling Salesman Problem (TSP). Grounded in \textsl{P
Externí odkaz:
http://arxiv.org/abs/2110.15105
Autor:
Feng, Xidong, Slumbers, Oliver, Wan, Ziyu, Liu, Bo, McAleer, Stephen, Wen, Ying, Wang, Jun, Yang, Yaodong
When solving two-player zero-sum games, multi-agent reinforcement learning (MARL) algorithms often create populations of agents where, at each iteration, a new agent is discovered as the best response to a mixture over the opponent population. Within
Externí odkaz:
http://arxiv.org/abs/2106.02745
Autor:
Nieves, Nicolas Perez, Yang, Yaodong, Slumbers, Oliver, Mguni, David Henry, Wen, Ying, Wang, Jun
Promoting behavioural diversity is critical for solving games with non-transitive dynamics where strategic cycles exist, and there is no consistent winner (e.g., Rock-Paper-Scissors). Yet, there is a lack of rigorous treatment for defining diversity
Externí odkaz:
http://arxiv.org/abs/2103.07927
Autor:
Dinh, Le Cong, Yang, Yaodong, McAleer, Stephen, Tian, Zheng, Nieves, Nicolas Perez, Slumbers, Oliver, Mguni, David Henry, Ammar, Haitham Bou, Wang, Jun
Publikováno v:
Transactions on Machine Learning Research 2022
Solving strategic games with huge action space is a critical yet under-explored topic in economics, operations research and artificial intelligence. This paper proposes new learning algorithms for solving two-player zero-sum normal-form games where t
Externí odkaz:
http://arxiv.org/abs/2103.07780
Autor:
Yang, Yaodong, Luo, Jun, Wen, Ying, Slumbers, Oliver, Graves, Daniel, Ammar, Haitham Bou, Wang, Jun, Taylor, Matthew E.
Multiagent reinforcement learning (MARL) has achieved a remarkable amount of success in solving various types of video games. A cornerstone of this success is the auto-curriculum framework, which shapes the learning process by continually creating ne
Externí odkaz:
http://arxiv.org/abs/2102.07659
Autor:
Dinh, Le Cong, Yang, Yaodong, McAleer, Stephen, Tian, Zheng, Nieves, Nicolas Perez, Slumbers, Oliver, Mguni, David Henry, Ammar, Haitham Bou, Wang, Jun
Solving strategic games with huge action space is a critical yet under-explored topic in economics, operations research and artificial intelligence. This paper proposes new learning algorithms for solving two-player zero-sum normal-form games where t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5f0d36f0bf59a8b453bbefe580c7de3c
https://eprints.soton.ac.uk/471822/
https://eprints.soton.ac.uk/471822/