{"total":35,"rows":[{"id":"2403.12451","title":"End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations","created":"2024-03-19","cited_by_count":17,"area":"deeprl"},{"id":"2506.17518","title":"A Survey of State Representation Learning for Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":17,"area":"deeprl"},{"id":"2505.19281","title":"A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning","created":"2025-05-25","cited_by_count":11,"area":"deeprl"},{"id":"2510.21110","title":"Confounding Robust Deep Reinforcement Learning: A Causal Approach","created":"2025-10-24","cited_by_count":7,"area":"deeprl"},{"id":"2510.14129","title":"Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL","created":"2025-10-15","cited_by_count":5,"area":"deeprl"},{"id":"2402.06503","title":"ACTER: Diverse and Actionable Counterfactual Sequences for Explaining and Diagnosing RL Policies","created":"2024-02-09","cited_by_count":4,"area":"deeprl"},{"id":"2411.12173","title":"SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks","created":"2024-11-19","cited_by_count":3,"area":"deeprl"},{"id":"2402.12685","title":"XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques","created":"2024-02-20","cited_by_count":2,"area":"deeprl"},{"id":"2408.08230","title":"Explaining an Agent's Future Beliefs through Temporally Decomposing Future Reward Estimators","created":"2024-08-15","cited_by_count":2,"area":"deeprl"},{"id":"2503.14973","title":"Behaviour Discovery and Attribution for Explainable Reinforcement Learning","created":"2025-03-19","cited_by_count":2,"area":"deeprl"},{"id":"2504.05393","title":"Interactive Explanations for Reinforcement-Learning Agents","created":"2025-04-07","cited_by_count":2,"area":"deeprl"},{"id":"2405.14629","title":"Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of Experiences","created":"2024-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2411.16120","title":"Why the Agent Made that Decision: Contrastive Explanation Learning for Reinforcement Learning","created":"2024-11-25","cited_by_count":1,"area":"deeprl"},{"id":"2501.04068","title":"Explainable Reinforcement Learning for Formula One Race Strategy","created":"2025-01-07","cited_by_count":1,"area":"deeprl"},{"id":"2504.11118","title":"Revealing Human Attention Patterns from Gameplay Analysis for Reinforcement Learning","created":"2025-04-15","cited_by_count":1,"area":"deeprl"},{"id":"2507.14901","title":"Learning Nonlinear Causal Reductions to Explain Reinforcement Learning Policies","created":"2025-07-20","cited_by_count":1,"area":"deeprl"},{"id":"2508.07452","title":"Stackelberg Coupling of Online Representation Learning and Reinforcement Learning","created":"2025-08-10","cited_by_count":1,"area":"deeprl"},{"id":"2510.19244","title":"Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments","created":"2025-10-22","cited_by_count":1,"area":"deeprl"},{"id":"2511.06094","title":"Approximating Shapley Explanations in Reinforcement Learning","created":"2025-11-08","cited_by_count":1,"area":"deeprl"},{"id":"2603.18084","title":"Uncovering Latent Phase Structures and Branching Logic in Locomotion Policies: A Case Study on HalfCheetah","created":"2026-03-18","cited_by_count":1,"area":"deeprl"},{"id":"2406.14214","title":"REVEAL-IT: REinforcement learning with Visibility of Evolving Agent poLicy for InTerpretability","created":"2024-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2406.14324","title":"Revealing the Learning Process in Reinforcement Learning Agents Through Attention-Oriented Metrics","created":"2024-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2408.02606","title":"Backward explanations via redefinition of predicates","created":"2024-08-05","cited_by_count":0,"area":"deeprl"},{"id":"2504.10071","title":"Pay Attention to What and Where? Interpretable Feature Extractor in Vision-based Deep Reinforcement Learning","created":"2025-04-14","cited_by_count":0,"area":"deeprl"},{"id":"2505.16833","title":"Strategically Linked Decisions in Long-Term Planning and Reinforcement Learning","created":"2025-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2506.17297","title":"SafeRL-Lite: A Lightweight, Explainable, and Constrained Reinforcement Learning Library","created":"2025-06-17","cited_by_count":0,"area":"deeprl"},{"id":"2511.20591","title":"Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learning","created":"2025-11-25","cited_by_count":0,"area":"deeprl"},{"id":"2512.06204","title":"Quantifying Memory Use in Reinforcement Learning with Temporal Range","created":"2025-12-05","cited_by_count":0,"area":"deeprl"},{"id":"2512.09909","title":"STACHE: Local Black-Box Explanations for Reinforcement Learning Policies","created":"2025-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2602.01196","title":"Unraveling the Hidden Dynamical Structure in Recurrent Neural Policies","created":"2026-02-01","cited_by_count":0,"area":"deeprl"},{"id":"2603.13257","title":"Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework","created":"2026-02-24","cited_by_count":0,"area":"deeprl"},{"id":"2607.11607","title":"Auditing the Risk Claims of Distributional Reinforcement Learning","created":"2026-07-13","cited_by_count":0,"area":"deeprl"},{"id":"2607.13655","title":"Explaining Reinforcement Learning Agents via Inductive Logic Programming","created":"2026-07-15","cited_by_count":0,"area":"deeprl"},{"id":"2607.22525","title":"Explainable Reinforcement Learning for assisting Air Traffic Controllers","created":"2026-07-24","cited_by_count":0,"area":"deeprl"},{"id":"2608.14620","title":"Explaining Reinforcement Learning Decisions in Self-adaptive Systems","created":"2026-07-13","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}