Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty

arXiv:2404.18909v1 Announce Type: new
Abstract: To overcome the sim-to-real gap in reinforcement learning (RL), learned policies must maintain robustness against environmental uncertainties. While robust RL has been widely studied in single-agent regimes, in multi-agent environments, the problem remains understudied -- despite the fact that the problems posed by environmental uncertainties are often exacerbated by strategic interactions. This work focuses on learning in distributionally robust Markov games (RMGs), a robust variant of standard Markov games, wherein each agent aims to learn …

abstract agent arxiv cs.lg environmental environments face gap multi-agent policies reinforcement reinforcement learning robust robustness sample sim stat.ml type uncertainty while