{"total":34,"rows":[{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42,"area":null},{"id":"2107.02776","title":"Counterfactual Explanations in Sequential Decision Making Under Uncertainty","created":"2021-07-06","cited_by_count":37,"area":null},{"id":"2301.09937","title":"Explainable Deep Reinforcement Learning: State of the Art and Challenges","created":"2023-01-24","cited_by_count":33,"area":null},{"id":"2302.12689","title":"GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanations","created":"2023-02-24","cited_by_count":17,"area":null},{"id":"2312.11118","title":"Explaining Reinforcement Learning Agents Through Counterfactual Action Outcomes","created":"2023-12-18","cited_by_count":14,"area":null},{"id":"2210.11846","title":"Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities","created":"2022-10-21","cited_by_count":13,"area":null},{"id":"2412.15619","title":"Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning","created":"2024-12-20","cited_by_count":11,"area":null},{"id":"2210.11825","title":"Integrating Policy Summaries with Reward Decomposition for Explaining Reinforcement Learning Agents","created":"2022-10-21","cited_by_count":10,"area":null},{"id":"2509.21044","title":"Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs","created":"2025-09-25","cited_by_count":9,"area":null},{"id":"2201.12462","title":"Explaining Reinforcement Learning Policies through Counterfactual Trajectories","created":"2022-01-29","cited_by_count":7,"area":null},{"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":"2305.04073","title":"Explaining RL Decisions with Trajectories","created":"2023-05-06","cited_by_count":7,"area":null},{"id":"2112.03020","title":"Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2404.16042","title":"How explainable AI affects human performance: A systematic review of the behavioural consequences of saliency maps","created":"2024-04-03","cited_by_count":6,"area":null},{"id":"2101.07312","title":"Benchmarking Perturbation-based Saliency Maps for Explaining Atari Agents","created":"2021-01-18","cited_by_count":4,"area":null},{"id":"2203.11211","title":"ReCCoVER: Detecting Causal Confusion for Explainable Reinforcement Learning","created":"2022-03-21","cited_by_count":4,"area":null},{"id":"2206.00152","title":"Human-AI Shared Control via Policy Dissection","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2205.08685","title":"Policy Distillation with Selective Input Gradient Regularization for Efficient Interpretability","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2307.13192","title":"Counterfactual Explanation Policies in RL","created":"2023-07-25","cited_by_count":2,"area":null},{"id":"2510.25775","title":"Towards Piece-by-Piece Explanations for Chess Positions with SHAP","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2210.02224","title":"Neural Distillation as a State Representation Bottleneck in Reinforcement Learning","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2210.13507","title":"Causal Explanation for Reinforcement Learning: Quantifying State and Temporal Importance","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2411.07200","title":"'Explaining RL Decisions with Trajectories': A Reproducibility Study","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2104.04893","title":"The Atari Data Scraper","created":"2021-04-11","cited_by_count":0,"area":null},{"id":"2211.04987","title":"Interpretable Deep Reinforcement Learning for Green Security Games with Real-Time Information","created":"2022-11-09","cited_by_count":0,"area":null},{"id":"2302.13483","title":"CrystalBox: Future-Based Explanations for Input-Driven Deep RL Systems","created":"2023-02-27","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":"2510.00274","title":"MAGIC-MASK: Multi-Agent Guided Inter-Agent Collaboration with Mask-Based Explainability for Reinforcement Learning","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2607.11486","title":"Communicating Chess Strategies in Natural Language","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.17861","title":"ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulation","created":"2026-07-20","cited_by_count":0,"area":null}],"next_cursor":null}