2021/07/30 by Robert Loftin, Aadirupa Saha, Loftin, Robert +5
Computer Science · Decision Sciences · #68T05 #Artificial Intelligence (cs.AI) #Auction Theory and Applications #FOS: Computer and information sciences #Game Theory and Applications #I.2.6 #Machine Learning (cs.LG) #Multiagent Systems (cs.MA) #Reinforcement Learning in Robotics
paper · pdf · doi:10.48550/arxiv.2107.14698
openalex publication_date 2021/07/30 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/29
High sample complexity remains a barrier to the application of reinforcement learning (RL), particularly in multi-agent systems. A large body of work has demonstrated that exploration mechanisms based on the principle of optimism under uncertainty can significantly improve the sample efficiency of RL in single agent tasks. This work seeks to understand the role of optimistic exploration in non-cooperative multi-agent settings. We will show that, in zero-sum games, optimistic exploration can cause the learner to waste time sampling parts of the state space that are irrelevant to strategic play, as they can only be reached through cooperation between both players. To address this issue, we introduce a formal notion of strategically efficient exploration in Markov games, and use this to develop two strategically efficient learning algorithms for finite Markov games. We demonstrate that these methods can be significantly more sample efficient than their optimistic counterparts.