{"ID":2843847,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.06881","arxiv_id":"2511.06881","title":"Reinforcement Learning Framework For Stochastic Optimal Control Problem Under Model Uncertainty","abstract":"We develop a continuous-time entropy-regularized reinforcement learning framework under model uncertainty. By applying Sion's minimax theorem, we transform the intractable robust control problem into an equivalent standard entropy-regularized stochastic control problem, facilitating reinforcement learning algorithms. We establish sufficient conditions for the theorem's validity and demonstrate our approach on linear-quadratic problems with uncertain model parameters following Bernoulli and uniform distributions.","short_abstract":"We develop a continuous-time entropy-regularized reinforcement learning framework under model uncertainty. By applying Sion's minimax theorem, we transform the intractable robust control problem into an equivalent standard entropy-regularized stochastic control problem, facilitating reinforcement learning algorithms. W...","url_abs":"https://arxiv.org/abs/2511.06881","url_pdf":"https://arxiv.org/pdf/2511.06881v1","authors":"[\"Jiaxuan Hou\",\"Lifeng Wei\"]","published":"2025-11-10T09:29:28Z","proceeding":"math.OC","tasks":"[\"math.OC\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}