{"ID":2836687,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.19849","arxiv_id":"2511.19849","title":"Reinforcement Learning with $ω$-Regular Objectives and Constraints","abstract":"Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of $ω$-regular objectives addresses this by precisely specifying rich behavioural properties. Even still, measuring performance by a single scalar (be it reward or satisfaction probability) masks safety-performance trade-offs that arise in settings with a tolerable level of risk. We address both limitations simultaneously by combining $ω$-regular objectives with explicit constraints, allowing safety requirements and optimisation targets to be treated separately. We develop a model-based RL algorithm based on linear programming, which in the limit produces a policy maximising the probability of satisfying an $ω$-regular objective while also adhering to $ω$-regular constraints within specified thresholds. Furthermore, we establish a translation to constrained limit-average problems with optimality-preserving guarantees.","short_abstract":"Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of $ω$-regular objectives addresses this by precisely specifying rich behavioural propertie...","url_abs":"https://arxiv.org/abs/2511.19849","url_pdf":"https://arxiv.org/pdf/2511.19849v1","authors":"[\"Dominik Wagner\",\"Leon Witzman\",\"Luke Ong\"]","published":"2025-11-25T02:28:02Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}