Corruption-robust Offline Two-player Zero-sum Markov Games

Abstract

We study data corruption robustness in offline two-player zero-sum Markov games. Given a dataset of realized trajectories of two players, an adversary is allowed to modify an \(\epsilon\)-fraction of it. The learner's goal is to identify an approximate Nash Equilibrium policy pair from the corrupted data. We consider this problem in linear Markov games under different degrees of data coverage and corruption. We start by providing an information-theoretic lower bound on the suboptimality gap of any learner. Next, we propose robust versions of the Pessimistic Minimax Value Iteration algorithm, both under coverage on the corrupted data and under coverage only on the clean data, and show that they achieve (near)-optimal suboptimality gap bounds with respect to \(\epsilon\). We note that we are the first to provide such a characterization of the problem of learning approximate Nash Equilibrium policies in offline two-player zero-sum Markov games under data corruption.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynika2024corruption

Related papers

• Corruption Robust Offline Reinforcement Learning With Human Feedback (2024)0.00
• Sparse Offline Reinforcement Learning With Corruption Robustness (2025)0.00
• Model-based Reinforcement Learning For Offline Zero-sum Markov Games (2022)0.00
• Corrupted Learning Dynamics In Games (2024)0.00
• Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning From Offline Datasets (2022)0.00
• Towards Robust Offline Reinforcement Learning Under Diverse Data Corruption (2023)0.00
• Regret Minimization And Convergence To Equilibria In General-sum Markov Games (2022)0.00
• Conservative Equilibrium Discovery In Offline Game-theoretic Multiagent Reinforcement Learning (2026)0.00