Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation

• URL: http://arxiv.org/abs/2203.07181v2
• Date: Fri, 11 Oct 2024 01:10:02 GMT
• Title: Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation
• Authors: Brian Zhang, Gabriele Farina, Andrea Celli, Tuomas Sandholm,
• Abstract summary: We study the problem of finding optimal correlated equilibria of various sorts in extensive-form games. We introduce a new algorithm for computing optimal equilibria in all three notions.
• Score: 78.48747645545944
• License:
• Abstract: We study the problem of finding optimal correlated equilibria of various sorts in extensive-form games: normal-form coarse correlated equilibrium (NFCCE), extensive-form coarse correlated equilibrium (EFCCE), and extensive-form correlated equilibrium (EFCE). We make two primary contributions. First, we introduce a new algorithm for computing optimal equilibria in all three notions. Its runtime depends exponentially only on a parameter related to the information structure of the game. We also prove a fundamental complexity gap: while our size bounds for NFCCE are similar to those achieved in the case of team games by Zhang et al., this is impossible to achieve for the other two concepts under standard complexity assumptions. Second, we propose a two-sided column generation approach for use when the runtime or memory usage of the previous algorithm is prohibitive. Our algorithm improves upon the one-sided approach of Farina et al. by means of a new decomposition of correlated strategies which allows players to re-optimize their sequence-form strategies with respect to correlation plans which were previously added to the support. Experiments show that our techniques outperform the prior state of the art for computing optimal general-sum correlated equilibria.

Related papers

• Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games [44.95137108337898]
  We provide an uncoupled policy optimization algorithm that attains a near-optimal $tildeO(T-1)$ convergence rate for computing a correlated equilibrium. Our algorithm is constructed by combining two main elements (i.e. smooth value updates and (ii. the optimistic-follow-the-regularized-leader algorithm with the log barrier regularizer)
  arXiv  Detail & Related papers  (2024-01-26T23:13:47Z)
• ALEXR: An Optimal Single-Loop Algorithm for Convex Finite-Sum Coupled Compositional Stochastic Optimization [53.14532968909759]
  We introduce an efficient single-loop primal-dual block-coordinate algorithm, dubbed ALEXR. We establish the convergence rates of ALEXR in both convex and strongly convex cases under smoothness and non-smoothness conditions. We present lower complexity bounds to demonstrate that the convergence rates of ALEXR are optimal among first-order block-coordinate algorithms for the considered class of cFCCO problems.
  arXiv  Detail & Related papers  (2023-12-04T19:00:07Z)
• The Computational Complexity of Single-Player Imperfect-Recall Games [37.550554344575]
  We study extensive-form games with imperfect recall, such as the Sleeping Beauty problem or the Absent Driver game. For such games, two natural equilibrium concepts have been proposed as alternative solution concepts to ex-ante optimality.
  arXiv  Detail & Related papers  (2023-05-28T19:41:25Z)
• Offline Learning in Markov Games with General Function Approximation [22.2472618685325]
  We study offline multi-agent reinforcement learning (RL) in Markov games. We provide the first framework for sample-efficient offline learning in Markov games.
  arXiv  Detail & Related papers  (2023-02-06T05:22:27Z)
• Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games [63.60117916422867]
  This paper focuses on the most basic setting of competitive multi-agent RL, namely two-player zero-sum Markov games. We propose a single-loop policy optimization method with symmetric updates from both agents, where the policy is updated via the entropy-regularized optimistic multiplicative weights update (OMWU) method. Our convergence results improve upon the best known complexities, and lead to a better understanding of policy optimization in competitive Markov games.
  arXiv  Detail & Related papers  (2022-10-03T16:05:43Z)
• Better Regularization for Sequential Decision Spaces: Fast Convergence Rates for Nash, Correlated, and Team Equilibria [121.36609493711292]
  We study the application of iterative first-order methods to the problem of computing equilibria of large-scale two-player extensive-form games. By instantiating first-order methods with our regularizers, we develop the first accelerated first-order methods for computing correlated equilibra and ex-ante coordinated team equilibria.
  arXiv  Detail & Related papers  (2021-05-27T06:10:24Z)
• Polynomial-Time Computation of Optimal Correlated Equilibria in Two-Player Extensive-Form Games with Public Chance Moves and Beyond [107.14897720357631]
  We show that an optimal correlated equilibrium can be computed in time in two-player games with public chance moves. This results in the biggest positive complexity result surrounding extensive-form correlation in more than a decade.
  arXiv  Detail & Related papers  (2020-09-09T14:51:58Z)

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.