no code implementations • 18 Dec 2023 • Hanyu Li, Wenhan Huang, Zhijian Duan, David Henry Mguni, Kun Shao, Jun Wang, Xiaotie Deng
This paper reviews various algorithms computing the Nash equilibrium and its approximation solutions in finite normal-form games from both theoretical and empirical perspectives.
no code implementations • 27 Oct 2023 • Xue Yan, Yan Song, Xinyu Cui, Filippos Christianos, Haifeng Zhang, David Henry Mguni, Jun Wang
To that purpose, we offer a new leader-follower bilevel framework that is capable of learning to ask relevant questions (prompts) and subsequently undertaking reasoning to guide the learning of actions.
no code implementations • 30 May 2022 • Oliver Slumbers, David Henry Mguni, Stephen Marcus McAleer, Stefano B. Blumberg, Jun Wang, Yaodong Yang
Although there are equilibrium concepts in game theory that take into account risk aversion, they either assume that agents are risk-neutral with respect to the uncertainty caused by the actions of other agents, or they are not guaranteed to exist.
no code implementations • 7 Oct 2021 • Le Cong Dinh, David Henry Mguni, Long Tran-Thanh, Jun Wang, Yaodong Yang
In this setting, we first demonstrate that MDP-Expert, an existing algorithm that works well with oblivious adversaries can still apply and achieve a policy regret bound of $\mathcal{O}(\sqrt{T \log(L)}+\tau^2\sqrt{ T \log(|A|)})$ where $L$ is the size of adversary's pure strategy set and $|A|$ denotes the size of agent's action space.
1 code implementation • NeurIPS 2021 • Jakub Grudzien Kuba, Muning Wen, Yaodong Yang, Linghui Meng, Shangding Gu, Haifeng Zhang, David Henry Mguni, Jun Wang
In multi-agent RL (MARL), although the PG theorem can be naturally extended, the effectiveness of multi-agent PG (MAPG) methods degrades as the variance of gradient estimates increases rapidly with the number of agents.
3 code implementations • 14 Mar 2021 • Nicolas Perez Nieves, Yaodong Yang, Oliver Slumbers, David Henry Mguni, Ying Wen, Jun Wang
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).
1 code implementation • 13 Mar 2021 • Le Cong Dinh, Yaodong Yang, Stephen Mcaleer, Zheng Tian, Nicolas Perez Nieves, Oliver Slumbers, David Henry Mguni, Haitham Bou Ammar, Jun Wang
Solving strategic games with huge action space is a critical yet under-explored topic in economics, operations research and artificial intelligence.