{"total":17,"rows":[{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2202.08434","title":"A Survey of Explainable Reinforcement Learning","created":"2022-02-17","cited_by_count":31,"area":null},{"id":"2205.12449","title":"MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learning","created":"2022-05-25","cited_by_count":12,"area":null},{"id":"2209.07225","title":"MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2305.10378","title":"Explainable Multi-Agent Reinforcement Learning for Temporal Queries","created":"2023-05-17","cited_by_count":9,"area":null},{"id":"2309.12701","title":"Breiman meets Bellman: Non-Greedy Decision Trees with MDPs","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2301.05753","title":"Fairness and Sequential Decision Making: Limits, Lessons, and Opportunities","created":"2023-01-13","cited_by_count":5,"area":null},{"id":"2211.06665","title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2503.06985","title":"Learning Decision Trees as Amortized Structure Inference","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2309.13365","title":"Limits of Actor-Critic Algorithms for Decision Tree Policies Learning in IBMDPs","created":"2023-09-23","cited_by_count":1,"area":null},{"id":"2409.03260","title":"In Search of Trees: Decision-Tree Policy Synthesis for Black-Box Systems via Search","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2304.05839","title":"Optimal Interpretability-Performance Trade-off of Classification Trees with Black-Box Reinforcement Learning","created":"2023-04-11","cited_by_count":0,"area":null},{"id":"2401.12243","title":"Constraint-Generation Policy Optimization (CGPO): Nonlinear Programming for Policy Optimization in Mixed Discrete-Continuous MDPs","created":"2024-01-20","cited_by_count":0,"area":null},{"id":"2503.10509","title":"From Actions to Words: Towards Abstractive-Textual Policy Summarization in RL","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2503.23326","title":"Exploring Explainable Multi-agent MCTS-minimax Hybrids in Board Game Using Process Mining","created":"2025-03-30","cited_by_count":0,"area":null},{"id":"2508.15652","title":"Understanding Action Effects through Instrumental Empowerment in Multi-Agent Reinforcement Learning","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2607.25925","title":"dtControl2+$\\varepsilon$: Trading Optimality for Explainability in MDPs via Decision Trees","created":"2026-07-28","cited_by_count":0,"area":null}],"next_cursor":null}