M Cheng, R Zhou, PR Kumar… - … Conference on Artificial …, 2024 - proceedings.mlr.press
We study Markov potential games under the infinite horizon average reward criterion. Most previous studies have been for discounted rewards. We prove that both algorithms based on …
P Jordan, A Barakat, N He - International Conference on …, 2024 - proceedings.mlr.press
Constrained Markov games offer a formal mathematical framework for modeling multi-agent reinforcement learning problems where the behavior of the agents is subject to constraints …
Independent learning (IL), despite being a popular approach in practice to achieve scalability in large-scale multi-agent systems, usually lacks global convergence guarantees …
S Aydin, C Eksin - 2023 62nd IEEE Conference on Decision …, 2023 - ieeexplore.ieee.org
We design a multi-agent and networked policy gradient algorithm in Markov potential games. Each agent has its own rewards and utility as functions of joint actions and a shared …
This paper proposes a new framework of Markov $\alpha $-potential games to study Markov games. In this new framework, Markov games are shown to be Markov $\alpha $-potential …
Markov games offer a formal mathematical framework for modeling multi-agent reinforcement learning problems. Markov Potential Games (MPGs) represent a subclass of …