{"total":8,"rows":[{"id":"2306.16208","title":"Continuous-time q-learning for mean-field control problems","created":"2023-06-28","cited_by_count":22,"area":null},{"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":"2503.21224","title":"Efficient Learning for Entropy-Regularized Markov Decision Processes via Multilevel Monte Carlo","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2403.17364","title":"A Moreau Envelope Approach for LQR Meta-Policy Estimation","created":"2024-03-26","cited_by_count":2,"area":null},{"id":"2602.16555","title":"Learning Distributed Equilibria in Linear-Quadratic Stochastic Differential Games: An $\\alpha$-Potential Approach","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2608.07433","title":"Wasserstein Policy Gradient for Entropy-Regularized Linear-Quadratic Control","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.14972","title":"Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence","created":"2026-09-14","cited_by_count":0,"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}