paper-with-me

홈 › Papers

Robust Asynchronous Q-Learning under Reward and State Corruption via Batching

2026-07-23 · Sreejeet Maity, Aritra Mitra arxiv

Motivated by reinforcement learning in harsh environments, we consider the problem of learning an optimal policy subject to adversarially corrupted feedback. Specifically, at each time-step, an adversary can perturb both the reward and state observations of the learner following the Huber contamination model. To defend against such data corruption, we propose {\texttt{BR-Async-Q}}: a novel, epoch-based, robust \(Q\)-learning algorithm built upon two key ideas: (i) partitioning the online data stream into batches to reduce variance, and (ii) constructing robust estimates of the Bellman optimality operator using such batched data. We prove a high-probability $\ell_\infty$ error bound for {\texttt{BR-Async-Q}} that matches that for vanilla \(Q\)-learning, up to a small additive term that scales with the fraction of corrupted samples. To our knowledge, this provides the first robustness guarantee for asynchronous \(Q\)-learning subject to both reward and state corruption. Furthermore, when only rewards are corrupted, the dependence of our algorithm's bound on the corruption fraction is minimax optimal.

📄 PDF Abstract BibTeX arXiv:2607.20822

Code (1)

arxivsub/arXivSub_daily_arxiv ★ 3

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates

2025-09-10 · Sreejeet Maity, Aritra Mitra arxiv

We study the problem of learning the optimal policy in a discounted, infinite-horizon reinforcement learning (RL) setting in the presence of adversarially corrupted rewards. To address this problem, we develop a novel ro…

Reinforcement Learning

Faster Stochastic Optimization with Arbitrary Delays via Asynchronous Mini-Batching

2024-08-14 · Amit Attia, Ofir Gaash, Tomer Koren

We consider the problem of asynchronous stochastic optimization, where an optimization algorithm makes updates based on stale stochastic gradients of the objective that are subject to an arbitrary (possibly adversarial) …

Stochastic Optimization

Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach

2025-05-26 · Swetha Ganesh, Vaneet Aggarwal

Actor-Critic methods are widely used for their scalability, yet existing theoretical guarantees for infinite-horizon average-reward Markov Decision Processes (MDPs) often rely on restrictive ergodicity assumptions. We pr…

TARvalid

Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching

2026-01-15 · Nadav Merlis arxiv

We study tabular reinforcement learning problems with multiple steps of lookahead information. Before acting, the learner observes $\ell$ steps of future transition and reward realizations: the exact state the agent woul…

Reinforcement Learning

MindGames Arena Generalization Track: In2AI Solution with Delayed Per-Step Reward Attribution

2026-04-13 · Aliaksei Korshuk, Alexander Buyantuev, Ilya Makarov arxiv

Training language model agents for multi-agent strategic interaction presents a core difficulty: the quality of any action may depend on future events that never materialize, on moves that violate game rules, or on decis…

Reinforcement Learning