{"slug": "robust-asynchronous-q-learning-under-reward-and-state-corruption-via-batching", "title": "Robust Asynchronous Q-Learning under Reward and State Corruption via Batching", "summary": "A new robust Q-learning algorithm, BR-Async-Q, achieves the first robustness guarantee for asynchronous Q-learning under both reward and state corruption, matching vanilla Q-learning error bounds up to a small additive term proportional to the corruption fraction. The algorithm, introduced in arXiv:2607.20822v1, uses epoch-based batching and robust Bellman operator estimates to defend against adversarial perturbations in harsh environments, with minimax optimal corruption dependence when only rewards are corrupted.", "body_md": "arXiv:2607.20822v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/robust-asynchronous-q-learning-under-reward-and-state-corruption-via-batching", "canonical_source": "https://www.machinebrief.com/news/robust-asynchronous-q-learning-under-reward-and-state-corrup-31vx", "published_at": "2026-07-24 04:00:00+00:00", "updated_at": "2026-07-24 04:38:53.725843+00:00", "lang": "en", "topics": ["machine-learning", "ai-safety", "ai-research"], "entities": ["BR-Async-Q", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/robust-asynchronous-q-learning-under-reward-and-state-corruption-via-batching", "markdown": "https://wpnews.pro/news/robust-asynchronous-q-learning-under-reward-and-state-corruption-via-batching.md", "text": "https://wpnews.pro/news/robust-asynchronous-q-learning-under-reward-and-state-corruption-via-batching.txt", "jsonld": "https://wpnews.pro/news/robust-asynchronous-q-learning-under-reward-and-state-corruption-via-batching.jsonld"}}