{"total":5,"rows":[{"id":"2405.20250","title":"Entropy annealing for policy mirror descent in continuous time and space","created":"2024-05-30","cited_by_count":12,"area":null},{"id":"2411.01302","title":"Regret of exploratory policy improvement and $q$-learning","created":"2024-11-02","cited_by_count":12,"area":null},{"id":"2310.17168","title":"Learning an Inventory Control Policy with General Inventory Arrival Dynamics","created":"2023-10-26","cited_by_count":5,"area":null},{"id":"2506.08121","title":"Continuous Policy and Value Iteration for Relaxed Stochastic Control Problems and Its Convergence","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2610.04285","title":"Amortized Score-Hamiltonian Policy Iteration: A Grid-Free Scheme for Relaxed Stochastic Control Problems","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}