{"total":44,"rows":[{"id":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64,"area":null},{"id":"2106.03787","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","created":"2021-06-07","cited_by_count":56,"area":null},{"id":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37,"area":null},{"id":"2207.02575","title":"Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design","created":"2022-07-06","cited_by_count":33,"area":null},{"id":"2303.08059","title":"Fast Rates for Maximum Entropy Exploration","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2306.11700","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","created":"2023-06-20","cited_by_count":28,"area":null},{"id":"2307.13372","title":"Submodular Reinforcement Learning","created":"2023-07-25","cited_by_count":23,"area":null},{"id":"2203.12592","title":"Your Policy Regularizer is Secretly an Adversary","created":"2022-03-23","cited_by_count":21,"area":null},{"id":"2302.01275","title":"ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2206.14332","title":"Active Exploration via Experiment Design in Markov Chains","created":"2022-06-29","cited_by_count":19,"area":null},{"id":"2302.02252","title":"Reinforcement Learning in Low-Rank MDPs with Density Features","created":"2023-02-04","cited_by_count":18,"area":null},{"id":"2306.01854","title":"Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space","created":"2023-06-02","cited_by_count":18,"area":null},{"id":"2306.09210","title":"Optimal Exploration for Model-Based RL in Nonlinear Systems","created":"2023-06-15","cited_by_count":18,"area":null},{"id":"2305.17568","title":"Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2308.09175","title":"Diversifying AI: Towards Creative Chess with AlphaZero","created":"2023-08-17","cited_by_count":15,"area":null},{"id":"2410.15474","title":"Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization","created":"2024-10-20","cited_by_count":14,"area":null},{"id":"2211.02105","title":"Geometry and convergence of natural policy gradient methods","created":"2022-11-03","cited_by_count":12,"area":null},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2110.07409","title":"The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2204.05176","title":"Towards Painless Policy Optimization for Constrained MDPs","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2306.13601","title":"Active Coverage for PAC Reinforcement Learning","created":"2023-06-23","cited_by_count":8,"area":null},{"id":"2310.02440","title":"Learning Diverse Skills for Local Navigation under Multi-constraint Optimality","created":"2023-10-03","cited_by_count":8,"area":null},{"id":"2411.03651","title":"Policy Aggregation","created":"2024-11-06","cited_by_count":8,"area":null},{"id":"2602.16796","title":"Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2306.07001","title":"Cancellation-Free Regret Bounds for Lagrangian Approaches in Constrained Markov Decision Processes","created":"2023-06-12","cited_by_count":7,"area":null},{"id":"2402.08406","title":"Transition Constrained Bayesian Optimization via Markov Decision Processes","created":"2024-02-13","cited_by_count":7,"area":null},{"id":"2210.00991","title":"Policy Gradient for Reinforcement Learning with General Utilities","created":"2022-10-03","cited_by_count":6,"area":null},{"id":"2406.12795","title":"The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2502.08365","title":"Towards Principled Unsupervised Multi-Agent Reinforcement Learning","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2510.26688","title":"FlowQ-Net: A Generative Framework for Automated Quantum Circuit Design","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2309.02669","title":"Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2309.03710","title":"A State Representation for Diminishing Rewards","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2409.15128","title":"The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes","created":"2024-09-23","cited_by_count":3,"area":null},{"id":"2410.16600","title":"Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2302.07938","title":"Scalable Multi-Agent Reinforcement Learning with General Utilities","created":"2023-02-15","cited_by_count":2,"area":null},{"id":"2501.04426","title":"Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2205.13718","title":"Off-Beat Multi-Agent Reinforcement Learning","created":"2022-05-27","cited_by_count":1,"area":null},{"id":"2312.17194","title":"Resilient Constrained Reinforcement Learning","created":"2023-12-28","cited_by_count":1,"area":null},{"id":"2505.15782","title":"Solving General-Utility Markov Decision Processes in the Single-Trial Regime with Online Planning","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2512.19057","title":"Efficient Personalization of Generative Models via Optimal Experimental Design","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2605.26373","title":"Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.09298","title":"Risk-Aware General-Utility Markov Decision Processes","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}