{"total":24,"rows":[{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2102.03765","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","created":"2021-02-07","cited_by_count":55,"area":null},{"id":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43,"area":null},{"id":"2101.09207","title":"Differentiable Trust Region Layers for Deep Reinforcement Learning","created":"2021-01-22","cited_by_count":25,"area":null},{"id":"2110.07940","title":"Wasserstein Unsupervised Reinforcement Learning","created":"2021-10-15","cited_by_count":22,"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":"2212.13936","title":"On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations","created":"2022-12-28","cited_by_count":19,"area":null},{"id":"2404.10976","title":"Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning","created":"2024-04-17","cited_by_count":18,"area":null},{"id":"2111.02994","title":"Towards an Understanding of Default Policies in Multitask Policy Optimization","created":"2021-11-04","cited_by_count":8,"area":null},{"id":"2210.11137","title":"Trust Region Policy Optimization with Optimal Transport Discrepancies: Duality and Algorithm for Continuous Actions","created":"2022-10-20","cited_by_count":8,"area":null},{"id":"2305.10411","title":"Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies","created":"2023-05-17","cited_by_count":8,"area":null},{"id":"2403.19253","title":"Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning","created":"2024-03-28","cited_by_count":7,"area":null},{"id":"2306.14133","title":"Provably Convergent Policy Optimization via Metric-aware Trust Region Methods","created":"2023-06-25","cited_by_count":6,"area":null},{"id":"2205.15379","title":"Truly Deterministic Policy Optimization","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2209.07696","title":"Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes","created":"2022-09-16","cited_by_count":3,"area":null},{"id":"2310.14509","title":"Iteratively Learn Diverse Strategies with State Distance Information","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2312.15474","title":"A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learning","created":"2023-12-24","cited_by_count":3,"area":null},{"id":"2506.05634","title":"AutoQD: Automatic Discovery of Diverse Behaviors with Quality-Diversity Optimization","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2102.07889","title":"Distributionally-Constrained Policy Optimization via Unbalanced Optimal Transport","created":"2021-02-15","cited_by_count":1,"area":null},{"id":"2111.06005","title":"Agent Spaces","created":"2021-11-11","cited_by_count":1,"area":null},{"id":"2207.08258","title":"Minimum Description Length Control","created":"2022-07-17","cited_by_count":0,"area":null},{"id":"2211.14469","title":"Transfer RL via the Undo Maps Formalism","created":"2022-11-26","cited_by_count":0,"area":null},{"id":"2308.00989","title":"Wasserstein Diversity-Enriched Regularizer for Hierarchical Reinforcement Learning","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2606.12200","title":"Implicit Neural Representations of Individual Behavior","created":"2026-06-10","cited_by_count":0,"area":null}],"next_cursor":null}