paper-with-me

Papers

Pessimism-Free Offline Learning in General-Sum Games via KL Regularization

2026-04-30 · Claire Chen, Yuheng Zhang arxiv

Offline multi-agent reinforcement learning in general-sum settings is challenged by the distribution shift between logged datasets and target equilibrium policies. While standard methods rely on manual pessimistic penalties, we demonstrate that KL regularization suffices to stabilize learning and achieve equilibrium recovery. We propose General-sum Anchored Nash Equilibrium (GANE), which recovers regularized Nash equilibria at an accelerated statistical rate of $\widetilde{O}(1/n)$. For computational tractability, we develop General-sum Anchored Mirror Descent (GAMD), an iterative algorithm converging to a Coarse Correlated Equilibrium at the standard rate of $\widetilde{O}(1/\sqrt{n}+1/T)$. These results establish KL regularization as a standalone mechanism for pessimism-free offline learning that achieves equivalent or accelerated rates in multi-player general-sum games.

📄 PDF Abstract BibTeX arXiv:2605.00264

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

Beyond Pessimism: Offline Learning in KL-regularized Games

2026-04-08 · Yuheng Zhang, Claire Chen, Nan Jiang arxiv

We study offline learning in KL-regularized two-player zero-sum games, where policies are optimized with respect to a fixed reference policy through KL regularization. Prior work relies on pessimistic value estimation to…

Offline Two-Player Zero-Sum Markov Games with KL Regularization

2026-05-13 · Claire Chen, Yuheng Zhang, Xinyu Liu, Zixuan Xie 외 arxiv

We study the problem of learning Nash equilibria in offline two-player zero-sum Markov games. While existing approaches often rely on explicit pessimism to address distribution shift, we show that KL regularization alone…

State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning

2022-11-28 · Chen Chen, Hongyao Tang, Yi Ma, Chao Wang 외

Pessimism is of great importance in offline reinforcement learning (RL). One broad category of offline RL algorithms fulfills pessimism by explicit or implicit behavior regularization. However, most of them only consider…

Offline RLQ-Learningreinforcement-learningReinforcement Learning+1

Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling

2024-06-05 · Imad Aouali, Victor-Emmanuel Brunel, David Rohde, Anna Korba

Off-policy learning (OPL) often involves minimizing a risk estimator based on importance weighting to correct bias from the logging policy used to collect data. However, this method can produce an estimator with a high v…

Generalization Bounds

Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage

2023-05-16 · NeurIPS 2023 11

In this paper, we study distributionally robust offline reinforcement learning (robust offline RL), which seeks to find an optimal policy purely from an offline dataset that can perform well in perturbed environments. In…

Offline RL