Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning

arXiv:2404.19292v1 Announce Type: cross
Abstract: This work designs and analyzes a novel set of algorithms for multi-agent reinforcement learning (MARL) based on the principle of information-directed sampling (IDS). These algorithms draw inspiration from foundational concepts in information theory, and are proven to be sample efficient in MARL settings such as two-player zero-sum Markov games (MGs) and multi-player general-sum MGs. For episodic two-player zero-sum MGs, we present three sample-efficient algorithms for learning Nash equilibrium. The basic algorithm, referred to as MAIDS, …

abstract agent algorithms arxiv concepts cs.it cs.lg cs.ma designs foundational information inspiration math.it multi-agent novel reinforcement reinforcement learning sample sampling set stat.ml theory type work