Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games

• URL: http://arxiv.org/abs/2308.08858v2
• Date: Wed, 5 Jun 2024 21:24:33 GMT
• Title: Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
• Authors: Songtao Feng, Ming Yin, Yu-Xiang Wang, Jing Yang, Yingbin Liang,
• Abstract summary: We show that a model-free stage-based Q-learning algorithm can enjoy the same optimality in the $H$ dependence as model-based algorithms. Our algorithm features a key novel design of updating the reference value functions as the pair of optimistic and pessimistic value functions.
• Score: 66.2085181793014
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The problem of two-player zero-sum Markov games has recently attracted increasing interests in theoretical studies of multi-agent reinforcement learning (RL). In particular, for finite-horizon episodic Markov decision processes (MDPs), it has been shown that model-based algorithms can find an $\epsilon$-optimal Nash Equilibrium (NE) with the sample complexity of $O(H^3SAB/\epsilon^2)$, which is optimal in the dependence of the horizon $H$ and the number of states $S$ (where $A$ and $B$ denote the number of actions of the two players, respectively). However, none of the existing model-free algorithms can achieve such an optimality. In this work, we propose a model-free stage-based Q-learning algorithm and show that it achieves the same sample complexity as the best model-based algorithm, and hence for the first time demonstrate that model-free algorithms can enjoy the same optimality in the $H$ dependence as model-based algorithms. The main improvement of the dependency on $H$ arises by leveraging the popular variance reduction technique based on the reference-advantage decomposition previously used only for single-agent RL. However, such a technique relies on a critical monotonicity property of the value function, which does not hold in Markov games due to the update of the policy via the coarse correlated equilibrium (CCE) oracle. Thus, to extend such a technique to Markov games, our algorithm features a key novel design of updating the reference value functions as the pair of optimistic and pessimistic value functions whose value difference is the smallest in the history in order to achieve the desired improvement in the sample efficiency.

Related papers

• Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation [44.051717720483595]
  This paper presents the first line of MARL algorithms that provably resolve the curse of multiagency approximation. In exchange for learning a weaker version of CCEs, this algorithm applies to a wider range of problems under generic function approximation. Our algorithm always outputs Markov CCEs, and an optimal rate of $widetildemathcalO(epsilon-2)$ for finding $epsilon$-optimal solutions.
  arXiv  Detail & Related papers  (2023-02-13T18:59:25Z)
• Representation Learning for General-sum Low-rank Markov Games [63.119870889883224]
  We study multi-agent general-sum Markov games with nonlinear function approximation. We focus on low-rank Markov games whose transition matrix admits a hidden low-rank structure on top of an unknown non-linear representation.
  arXiv  Detail & Related papers  (2022-10-30T22:58:22Z)
• Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning [52.76230802067506]
  A novel model-free algorithm is proposed to minimize regret in episodic reinforcement learning. The proposed algorithm employs an em early-settled reference update rule, with the aid of two Q-learning sequences. The design principle of our early-settled variance reduction method might be of independent interest to other RL settings.
  arXiv  Detail & Related papers  (2021-10-09T21:13:48Z)
• Towards General Function Approximation in Zero-Sum Markov Games [126.58493169301012]
  This paper considers two-player zero-sum finite-horizon Markov games with simultaneous moves. Provably efficient algorithms for both decoupled and coordinated settings are developed.
  arXiv  Detail & Related papers  (2021-07-30T15:25:13Z)
• A Sharp Analysis of Model-based Reinforcement Learning with Self-Play [49.88233710867315]
  We present a sharp analysis of model-based self-play algorithms for multi-agent Markov games. We design an algorithm -- Optimistic Nash Value Iteration (Nash-VI) for two-player zero-sum Markov games. We further adapt our analysis to designing a provably efficient task-agnostic algorithm for zero-sum Markov games.
  arXiv  Detail & Related papers  (2020-10-04T15:27:39Z)
• Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity [67.02490430380415]
  We show that model-based MARL achieves a sample complexity of $tilde O(|S||B|(gamma)-3epsilon-2)$ for finding the Nash equilibrium (NE) value up to some $epsilon$ error. We also show that such a sample bound is minimax-optimal (up to logarithmic factors) if the algorithm is reward-agnostic, where the algorithm queries state transition samples without reward knowledge.
  arXiv  Detail & Related papers  (2020-07-15T03:25:24Z)
• A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret [44.374427255708135]
  We propose Exploration Enhanced Q-learning (EE-QL), a model-free algorithm for infinite-horizon average-reward Markov Decision Processes (MDPs) EE-QL assumes that an online concentrating approximation of the optimal average reward is available. This is the first model-free learning algorithm that achieves $O(sqrt T)$ regret without the ergodic assumption, and matches the lower bound in terms of $T$ except for logarithmic factors.
  arXiv  Detail & Related papers  (2020-06-08T05:09:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.