{"total":56,"rows":[{"id":"2107.04050","title":"Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning","created":"2021-07-08","cited_by_count":38,"area":null},{"id":"2203.11973","title":"Scalable Deep Reinforcement Learning Algorithms for Mean Field Games","created":"2022-03-22","cited_by_count":38,"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":"2202.01511","title":"Challenging Common Assumptions in Convex Reinforcement Learning","created":"2022-02-03","cited_by_count":30,"area":"offlinerl"},{"id":"2109.09717","title":"Generalization in Mean Field Games by Learning Master Policies","created":"2021-09-20","cited_by_count":28,"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":"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":"2305.11283","title":"On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation","created":"2023-05-18","cited_by_count":14,"area":null},{"id":"2306.14799","title":"On Imitation in Mean-field Games","created":"2023-06-26","cited_by_count":10,"area":"offlinerl"},{"id":"2310.08089","title":"Learning Regularized Monotone Graphon Mean-Field Games","created":"2023-10-12","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":"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":"2402.05757","title":"When is Mean-Field Reinforcement Learning Tractable and Relevant?","created":"2024-02-08","cited_by_count":8,"area":"deeprl"},{"id":"2203.08542","title":"Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act","created":"2022-03-16","cited_by_count":7,"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":"2208.00088","title":"Improved Policy Optimization for Online Imitation Learning","created":"2022-07-29","cited_by_count":6,"area":"offlinerl"},{"id":"2208.10138","title":"Learning Correlated Equilibria in Mean-Field Games","created":"2022-08-22","cited_by_count":6,"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":"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":"2403.03552","title":"Population-aware Online Mirror Descent for Mean-Field Games by Deep Reinforcement Learning","created":"2024-03-06","cited_by_count":5,"area":"deeprl"},{"id":"2405.00282","title":"MF-OML: Online Mean-Field Reinforcement Learning with Occupation Measures for Large Population Games","created":"2024-05-01","cited_by_count":5,"area":"deeprl"},{"id":"2405.19807","title":"MetaCURL: Non-stationary Concave Utility Reinforcement Learning","created":"2024-05-30","cited_by_count":4,"area":"deeprl"},{"id":"2509.03030","title":"Population-aware Online Mirror Descent for Mean-Field Games with Common Noise by Deep Reinforcement Learning","created":"2025-09-03","cited_by_count":4,"area":"deeprl"},{"id":"2107.00839","title":"Exploration noise for learning linear-quadratic mean field games","created":"2021-07-02","cited_by_count":3,"area":null},{"id":"2408.04780","title":"Learning in Herding Mean Field Games: Single-Loop Algorithm with Finite-Time Convergence Analysis","created":"2024-08-08","cited_by_count":3,"area":"deeprl"},{"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":"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":"2209.10958","title":"Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environments","created":"2022-09-22","cited_by_count":2,"area":null},{"id":"2210.09957","title":"Contextual bandits with concave rewards, and an application to fair ranking","created":"2022-10-18","cited_by_count":2,"area":null},{"id":"2405.19024","title":"Inverse Concave-Utility Reinforcement Learning is Inverse Game Theory","created":"2024-05-29","cited_by_count":2,"area":"offlinerl"},{"id":"2505.22781","title":"Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2510.22158","title":"Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics","created":"2025-10-25","cited_by_count":2,"area":"deeprl"},{"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":"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":"2602.12517","title":"Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games","created":"2026-02-13","cited_by_count":1,"area":"deeprl"},{"id":"2605.08946","title":"A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets","created":"2026-05-09","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":"2608.03562","title":"Robust General Utility for Reinforcement Learning","created":"2026-08-04","cited_by_count":1,"area":"deeprl"},{"id":"2211.03521","title":"On the importance of data collection for training general goal-reaching policies","created":"2022-11-07","cited_by_count":0,"area":null},{"id":"2302.08190","title":"Reimagining Demand-Side Management with Mean Field Learning","created":"2023-02-16","cited_by_count":0,"area":null},{"id":"2306.02766","title":"Networked Communication for Decentralised Agents in Mean-Field Games","created":"2023-06-05","cited_by_count":0,"area":null},{"id":"2410.05127","title":"Last Iterate Convergence in Monotone Mean Field Games","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2505.07303","title":"Online Episodic Convex Reinforcement Learning","created":"2025-05-12","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":"2606.22579","title":"Stationary Robust Mean-Field Games under Model Mismatches","created":"2026-06-21","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":"2609.04005","title":"The Dually Flat Geometry of Planning as Inference","created":"2026-09-03","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}