Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits

Qinghua Liu, Yuanhao Wang, Chi Jin

Research output: Contribution to journalConference articlepeer-review

2 Scopus citations

Abstract

An ideal strategy in zero-sum games should not only grant the player an average reward no less than the value of Nash equilibrium, but also exploit the (adaptive) opponents when they are suboptimal. While most existing works in Markov games focus exclusively on the former objective, it remains open whether we can achieve both objectives simultaneously. To address this problem, this work studies no-regret learning in Markov games with adversarial opponents when competing against the best fixed policy in hindsight. Along this direction, we present a new complete set of positive and negative results: When the policies of the opponents are revealed at the end of each episode, we propose new efficient algorithms achievingK-regret bounds when either (1) the baseline policy class is small or (2) the opponent's policy class is small. This is complemented with an exponential lower bound when neither conditions are true. When the policies of the opponents are not revealed, we prove a statistical hardness result even in the most favorable scenario when both above conditions are true. Our hardness result is much stronger than the existing hardness results which either only involve computational hardness, or require further restrictions on the algorithms.

Original languageEnglish (US)
Pages (from-to)14036-14053
Number of pages18
JournalProceedings of Machine Learning Research
Volume162
StatePublished - 2022
Event39th International Conference on Machine Learning, ICML 2022 - Baltimore, United States
Duration: Jul 17 2022Jul 23 2022

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits'. Together they form a unique fingerprint.

Cite this