Provably Convergent Actor-Critic in Risk-averse MARL

• URL: http://arxiv.org/abs/2602.12386v1
• Date: Thu, 12 Feb 2026 20:29:41 GMT
• Title: Provably Convergent Actor-Critic in Risk-averse MARL
• Authors: Yizhou Zhang, Eric Mazumdar,
• Abstract summary: We study Risk-averse Quantal response Equilibria (RQE), a solution concept rooted in behavioral game theory that incorporates risk aversion and bounded rationality.<n>We propose a novel two-timescale Actor-Critic algorithm characterized by a fast-timescale actor and a slow-timescale critic.
• Score: 15.77454427706097
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning stationary policies in infinite-horizon general-sum Markov games (MGs) remains a fundamental open problem in Multi-Agent Reinforcement Learning (MARL). While stationary strategies are preferred for their practicality, computing stationary forms of classic game-theoretic equilibria is computationally intractable -- a stark contrast to the comparative ease of solving single-agent RL or zero-sum games. To bridge this gap, we study Risk-averse Quantal response Equilibria (RQE), a solution concept rooted in behavioral game theory that incorporates risk aversion and bounded rationality. We demonstrate that RQE possesses strong regularity conditions that make it uniquely amenable to learning in MGs. We propose a novel two-timescale Actor-Critic algorithm characterized by a fast-timescale actor and a slow-timescale critic. Leveraging the regularity of RQE, we prove that this approach achieves global convergence with finite-sample guarantees. We empirically validate our algorithm in several environments to demonstrate superior convergence properties compared to risk-neutral baselines.

Related papers

• Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning [37.80275600302316]
  distributionally robust Markov games (RMGs) have been proposed to enhance robustness in MARL.<n>Two notorious and open challenges are the formulation of the uncertainty set and whether the corresponding RMGs can overcome the curse of multiagency.<n>In this work, we propose a natural class of RMGs inspired by behavioral economics, where each agent's uncertainty set is shaped by both the environment and the integrated behavior of other agents.
  arXiv  Detail & Related papers  (2024-09-30T08:09:41Z)
• Tractable Equilibrium Computation in Markov Games through Risk Aversion [12.980882140751895]
  We show that risk-averse quantal response equilibria (RQE) become tractable to compute in all $n$-player matrix and finite-horizon Markov games. RQE is independent of the underlying game structure and only depends on agents' degree of risk-aversion and bounded rationality.
  arXiv  Detail & Related papers  (2024-06-20T09:53:56Z)
• Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approach [2.3020018305241337]
  This paper is the first to propose considering the RRL problems within the positional differential game theory. Namely, we prove that under Isaacs's condition, the same Q-function can be utilized as an approximate solution of both minimax and maximin Bellman equations. We present the Isaacs Deep Q-Network algorithms and demonstrate their superiority compared to other baseline RRL and Multi-Agent RL algorithms in various environments.
  arXiv  Detail & Related papers  (2024-05-03T12:21:43Z)
• Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning [50.92957910121088]
  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) For episodic two-player zero-sum MGs, we present three sample-efficient algorithms for learning Nash equilibrium. We extend Reg-MAIDS to multi-player general-sum MGs and prove that it can learn either the Nash equilibrium or coarse correlated equilibrium in a sample efficient manner.
  arXiv  Detail & Related papers  (2024-04-30T06:48:56Z)
• Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty [40.55653383218379]
  This work focuses on learning in distributionally robust Markov games (RMGs) We propose a sample-efficient model-based algorithm (DRNVI) with finite-sample complexity guarantees for learning robust variants of various notions of game-theoretic equilibria.
  arXiv  Detail & Related papers  (2024-04-29T17:51:47Z)
• Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL [57.745700271150454]
  We study the sample complexity of reinforcement learning in Mean-Field Games (MFGs) with model-based function approximation. We introduce the Partial Model-Based Eluder Dimension (P-MBED), a more effective notion to characterize the model class complexity.
  arXiv  Detail & Related papers  (2024-02-08T14:54:47Z)
• Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula [23.80052541774509]
  Adversarial Reinforcement Learning trains a protagonist against destabilizing forces exercised by an adversary in a competitive zero-sum Markov game. Finding Nash equilibria requires facing complex saddle point optimization problems, which can be prohibitive to solve. We propose a novel approach for adversarial RL based on entropy regularization to ease the complexity of the saddle point optimization problem.
  arXiv  Detail & Related papers  (2023-11-03T00:00:32Z)
• 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)
• Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation [93.52573037053449]
  H-MARL (Hallucinated Multi-Agent Reinforcement Learning) learns successful equilibrium policies after a few interactions with the environment. We demonstrate our approach experimentally on an autonomous driving simulation benchmark.
  arXiv  Detail & Related papers  (2022-03-14T17:24:03Z)
• Robust Reinforcement Learning using Adversarial Populations [118.73193330231163]
  Reinforcement Learning (RL) is an effective tool for controller design but can struggle with issues of robustness. We show that using a single adversary does not consistently yield robustness to dynamics variations under standard parametrizations of the adversary. We propose a population-based augmentation to the Robust RL formulation in which we randomly initialize a population of adversaries and sample from the population uniformly during training.
  arXiv  Detail & Related papers  (2020-08-04T20:57:32Z)
• SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning [102.78958681141577]
  We present SUNRISE, a simple unified ensemble method, which is compatible with various off-policy deep reinforcement learning algorithms. SUNRISE integrates two key ingredients: (a) ensemble-based weighted Bellman backups, which re-weight target Q-values based on uncertainty estimates from a Q-ensemble, and (b) an inference method that selects actions using the highest upper-confidence bounds for efficient exploration.
  arXiv  Detail & Related papers  (2020-07-09T17:08:44Z)

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.