Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback

• URL: http://arxiv.org/abs/2603.28281v1
• Date: Mon, 30 Mar 2026 11:03:36 GMT
• Title: Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback
• Abstract summary: We consider robustness against data corruption in offline multi-agent reinforcement learning from human feedback.<n>We model the problem using the framework of linear Markov games.<n>To the best of our knowledge, this is the first systematic treatment of data corruption in offline MARLHF.
• Score: 26.662444975280792
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider robustness against data corruption in offline multi-agent reinforcement learning from human feedback (MARLHF) under a strong-contamination model: given a dataset $D$ of trajectory-preference tuples (each preference being an $n$-dimensional binary label vector representing each of the $n$ agents' preferences), an $ε$-fraction of the samples may be arbitrarily corrupted. We model the problem using the framework of linear Markov games. First, under a uniform coverage assumption - where every policy of interest is sufficiently represented in the clean (prior to corruption) data - we introduce a robust estimator that guarantees an $O(ε^{1 - o(1)})$ bound on the Nash equilibrium gap. Next, we move to the more challenging unilateral coverage setting, in which only a Nash equilibrium and its single-player deviations are covered. In this case, our proposed algorithm achieves an $O(\sqrtε)$ bound on the Nash gap. Both of these procedures, however, suffer from intractable computation. To address this, we relax our solution concept to coarse correlated equilibria (CCE). Under the same unilateral coverage regime, we derive a quasi-polynomial-time algorithm whose CCE gap scales as $O(\sqrtε)$. To the best of our knowledge, this is the first systematic treatment of adversarial data corruption in offline MARLHF.

Related papers

• Reinforcement Learning from Multi-Source Imperfect Preferences: Best-of-Both-Regimes Regret [71.69884486156359]
  We study episodic RL from emphmulti-source imperfect preferences through a cumulative imperfection budget.<n>We propose a unified algorithm with regret $tildeO(sqrtK/M+)$, which exhibits a best-of-both-regimes behavior.
  arXiv  Detail & Related papers  (2026-03-20T19:34:53Z)
• Communication-Corruption Coupling and Verification in Cooperative Multi-Objective Bandits [2.1772197319352498]
  We study cooperative multi-armed bandits with vector-valued rewards under adversarial corruption and limited verification.<n>We show that a fixed environment-side budget $$ can translate into an effective corruption level ranging from $$ to $N$.<n>We further establish information-theoretic limits, including an unavoidable additive $()$ penalty and a high-corruption regime $=(NT)$ where sublinear regret is impossible without clean information.
  arXiv  Detail & Related papers  (2026-01-17T06:13:52Z)
• Corruption-Robust Offline Two-Player Zero-Sum Markov Games [23.530166315532828]
  We study data corruption robustness in offline two-player zero-sum Markov games. We consider this problem in linear Markov games under different degrees of data coverage and corruption.
  arXiv  Detail & Related papers  (2024-03-04T12:48:25Z)
• Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption [60.958746600254884]
  This study tackles the challenges of adversarial corruption in model-based reinforcement learning (RL) We introduce an algorithm called corruption-robust optimistic MLE (CR-OMLE), which leverages total-variation (TV)-based information ratios as uncertainty weights for MLE. We extend our weighting technique to the offline setting, and propose an algorithm named corruption-robust pessimistic MLE (CR-PMLE)
  arXiv  Detail & Related papers  (2024-02-14T07:27:30Z)
• Corruption-Robust Offline Reinforcement Learning with General Function Approximation [60.91257031278004]
  We investigate the problem of corruption in offline reinforcement learning (RL) with general function approximation. Our goal is to find a policy that is robust to such corruption and minimizes the suboptimality gap with respect to the optimal policy for the uncorrupted Markov decision processes (MDPs)
  arXiv  Detail & Related papers  (2023-10-23T04:07:26Z)
• Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes [59.61248760134937]
  We propose an efficient algorithm to achieve a regret of $tildeO(sqrtT+zeta)$. The proposed algorithm relies on the recently developed uncertainty-weighted least-squares regression from linear contextual bandit. We generalize our algorithm to the episodic MDP setting and first achieve an additive dependence on the corruption level $zeta$.
  arXiv  Detail & Related papers  (2022-12-12T15:04:56Z)
• A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits [118.22458816174144]
  We propose a novel robust elimination-type algorithm that runs in epochs, combines exploration with infrequent switching to select a small subset of actions, and plays each action for multiple time instants. Our algorithm, GP Robust Phased Elimination (RGP-PE), successfully balances robustness to corruptions with exploration and exploitation. We perform the first empirical study of robustness in the corrupted GP bandit setting, and show that our algorithm is robust against a variety of adversarial attacks.
  arXiv  Detail & Related papers  (2022-02-03T21:19:36Z)
• Linear Contextual Bandits with Adversarial Corruptions [91.38793800392108]
  We study the linear contextual bandit problem in the presence of adversarial corruption. We present a variance-aware algorithm that is adaptive to the level of adversarial contamination $C$.
  arXiv  Detail & Related papers  (2021-10-25T02:53:24Z)

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.