{"total":84,"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":"2202.01511","title":"Challenging Common Assumptions in Convex Reinforcement Learning","created":"2022-02-03","cited_by_count":30,"area":"offlinerl"},{"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":"2209.07899","title":"Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions","created":"2022-09-16","cited_by_count":21,"area":"offlinerl"},{"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":"2511.22640","title":"Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning","created":"2025-11-27","cited_by_count":17,"area":"diffusion"},{"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":"2407.09905","title":"Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods","created":"2024-07-13","cited_by_count":15,"area":"deeprl"},{"id":"2110.06539","title":"On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning","created":"2021-10-13","cited_by_count":14,"area":"offlinerl"},{"id":"2407.10583","title":"Three Dogmas of Reinforcement Learning","created":"2024-07-15","cited_by_count":14,"area":"deeprl"},{"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":"2305.00303","title":"A Coupled Flow Approach to Imitation Learning","created":"2023-04-29","cited_by_count":12,"area":"offlinerl"},{"id":"2409.17401","title":"Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference","created":"2024-09-25","cited_by_count":12,"area":"alignment"},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2408.16286","title":"Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form","created":"2024-08-29","cited_by_count":10,"area":"deeprl"},{"id":"2510.04088","title":"Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees","created":"2025-10-05","cited_by_count":10,"area":"offlinerl"},{"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":"2401.14811","title":"On the Limitations of Markovian Rewards to Express Multi-Objective, Risk-Sensitive, and Modal Tasks","created":"2024-01-26","cited_by_count":9,"area":"deeprl"},{"id":"2204.05176","title":"Towards Painless Policy Optimization for Constrained MDPs","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2305.14608","title":"Inverse Reinforcement Learning with the Average Reward Criterion","created":"2023-05-24","cited_by_count":8,"area":"offlinerl"},{"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":"2501.11533","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","created":"2025-01-20","cited_by_count":8,"area":"deeprl"},{"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":"2405.13136","title":"Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs","created":"2024-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2208.00088","title":"Improved Policy Optimization for Online Imitation Learning","created":"2022-07-29","cited_by_count":6,"area":"offlinerl"},{"id":"2210.00991","title":"Policy Gradient for Reinforcement Learning with General Utilities","created":"2022-10-03","cited_by_count":6,"area":null},{"id":"2401.17780","title":"A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees","created":"2024-01-31","cited_by_count":6,"area":"deeprl"},{"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":"2407.13364","title":"Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction","created":"2024-07-18","cited_by_count":6,"area":"deeprl"},{"id":"2410.04108","title":"On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning","created":"2024-10-05","cited_by_count":6,"area":"offlinerl"},{"id":"2410.05673","title":"Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem","created":"2024-10-08","cited_by_count":5,"area":"deeprl"},{"id":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2405.19807","title":"MetaCURL: Non-stationary Concave Utility Reinforcement Learning","created":"2024-05-30","cited_by_count":4,"area":"deeprl"},{"id":"2406.07455","title":"Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis","created":"2024-06-11","cited_by_count":4,"area":"alignment"},{"id":"2412.14002","title":"Operator Splitting for Convex Constrained Markov Decision Processes","created":"2024-12-18","cited_by_count":4,"area":"deeprl"},{"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":"2506.00700","title":"Central Path Proximal Policy Optimization","created":"2025-05-31","cited_by_count":3,"area":"deeprl"},{"id":"2602.06769","title":"Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities","created":"2026-02-06","cited_by_count":3,"area":"deeprl"},{"id":"2302.07938","title":"Scalable Multi-Agent Reinforcement Learning with General Utilities","created":"2023-02-15","cited_by_count":2,"area":null},{"id":"2402.10810","title":"Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning","created":"2024-02-16","cited_by_count":2,"area":"deeprl"},{"id":"2405.19024","title":"Inverse Concave-Utility Reinforcement Learning is Inverse Game Theory","created":"2024-05-29","cited_by_count":2,"area":"offlinerl"},{"id":"2501.04426","title":"Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2602.08012","title":"A Unified Density Operator View of Flow Control and Merging","created":"2026-02-08","cited_by_count":2,"area":"diffusion"},{"id":"2603.08518","title":"Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning","created":"2026-03-09","cited_by_count":2,"area":"deeprl"},{"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":"2404.16468","title":"A Dual Perspective of Reinforcement Learning for Imposing Policy Constraints","created":"2024-04-25","cited_by_count":1,"area":"deeprl"},{"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":"2509.01432","title":"The Geometry of Nonlinear Reinforcement Learning","created":"2025-09-01","cited_by_count":1,"area":"deeprl"},{"id":"2602.12181","title":"Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria","created":"2026-02-12","cited_by_count":1,"area":"deeprl"},{"id":"2607.20152","title":"Active Inference as a Convex Markov Decision Process","created":"2026-07-22","cited_by_count":1,"area":"deeprl"},{"id":"2408.10015","title":"Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs","created":"2024-08-19","cited_by_count":0,"area":"deeprl"},{"id":"2505.04822","title":"Is there Value in Reinforcement Learning?","created":"2025-05-07","cited_by_count":0,"area":"deeprl"},{"id":"2505.07303","title":"Online Episodic Convex Reinforcement Learning","created":"2025-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2512.19057","title":"Efficient Personalization of Generative Models via Optimal Experimental Design","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2602.24182","title":"Multi-Objective Reinforcement Learning for Large-Scale Tote Allocation in Human-Robot Collaborative Fulfillment Centers","created":"2026-02-27","cited_by_count":0,"area":"deeprl"},{"id":"2604.28144","title":"Global Optimality for Constrained Exploration via Penalty Regularization","created":"2026-04-30","cited_by_count":0,"area":"deeprl"},{"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":"2606.25012","title":"Bias-Controlled Primal-Dual Natural Actor-Critic: Optimal Rates for Constrained Multi-Objective Average-Reward RL","created":"2026-06-23","cited_by_count":0,"area":"deeprl"},{"id":"2607.09298","title":"Risk-Aware General-Utility Markov Decision Processes","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.17823","title":"Theoretical Foundations of $\\max$@$k$ Reinforcement Learning","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2609.04005","title":"The Dually Flat Geometry of Planning as Inference","created":"2026-09-03","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}