{"total":60,"rows":[{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511,"area":null},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"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":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2206.01794","title":"Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology","created":"2022-06-03","cited_by_count":58,"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":"2101.12446","title":"Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning","created":"2021-01-29","cited_by_count":39,"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":"2209.09203","title":"Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning","created":"2022-09-16","cited_by_count":34,"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":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2305.02749","title":"Explainable Reinforcement Learning via a Causal World Model","created":"2023-05-04","cited_by_count":22,"area":"wm"},{"id":"2402.02423","title":"Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback","created":"2024-02-04","cited_by_count":21,"area":"alignment"},{"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":"2403.10940","title":"ViSaRL: Visual Reinforcement Learning Guided by Human Saliency","created":"2024-03-16","cited_by_count":12,"area":"deeprl"},{"id":"2106.05506","title":"Brittle AI, Causal Confusion, and Bad Mental Models: Challenges and Successes in the XAI Program","created":"2021-06-10","cited_by_count":11,"area":null},{"id":"2405.01636","title":"Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Survey","created":"2024-05-02","cited_by_count":11,"area":null},{"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":"2305.10378","title":"Explainable Multi-Agent Reinforcement Learning for Temporal Queries","created":"2023-05-17","cited_by_count":9,"area":null},{"id":"2310.07747","title":"Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples","created":"2023-10-11","cited_by_count":9,"area":"offlinerl"},{"id":"2503.06343","title":"Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning","created":"2025-03-08","cited_by_count":8,"area":"deeprl"},{"id":"2403.12176","title":"Safety Implications of Explainable Artificial Intelligence in End-to-End Autonomous Driving","created":"2024-03-18","cited_by_count":7,"area":"driving"},{"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":"2211.09937","title":"Explainability Via Causal Self-Talk","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2502.12530","title":"Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations","created":"2025-02-18","cited_by_count":6,"area":"alignment"},{"id":"2111.03995","title":"Explainable Deep Reinforcement Learning for Portfolio Management: An Empirical Approach","created":"2021-11-07","cited_by_count":5,"area":null},{"id":"2406.15042","title":"Behaviour Distillation","created":"2024-06-21","cited_by_count":5,"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":"2206.00152","title":"Human-AI Shared Control via Policy Dissection","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2310.05086","title":"Learning Generalizable Agents via Saliency-Guided Features Decorrelation","created":"2023-10-08","cited_by_count":4,"area":null},{"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":"2311.11396","title":"Towards interpretable-by-design deep learning algorithms","created":"2023-11-19","cited_by_count":3,"area":null},{"id":"2311.11491","title":"On the Relationship Between Interpretability and Explainability in Machine Learning","created":"2023-11-20","cited_by_count":3,"area":null},{"id":"2405.15661","title":"Exposing Image Classifier Shortcuts with Counterfactual Frequency (CoF) Tables","created":"2024-05-24","cited_by_count":3,"area":null},{"id":"2509.04809","title":"TalkToAgent: A Human-centric Explanation of Reinforcement Learning Agents with Large Language Models","created":"2025-09-05","cited_by_count":3,"area":"agents"},{"id":"2404.07725","title":"Unraveling the Dilemma of AI Errors: Exploring the Effectiveness of Human and Machine Explanations for Large Language Models","created":"2024-04-11","cited_by_count":2,"area":null},{"id":"2108.05701","title":"An Approach to Partial Observability in Games: Learning to Both Act and Observe","created":"2021-08-11","cited_by_count":1,"area":null},{"id":"2201.06274","title":"Detecting danger in gridworlds using Gromov's Link Condition","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2205.10911","title":"Power and accountability in reinforcement learning applications to environmental policy","created":"2022-05-22","cited_by_count":1,"area":null},{"id":"2312.03762","title":"Colour versus Shape Goal Misgeneralization in Reinforcement Learning: A Case Study","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2512.13837","title":"Explainable reinforcement learning from human feedback to improve alignment","created":"2025-12-15","cited_by_count":1,"area":"alignment"},{"id":"2603.23738","title":"BXRL: Behavior-Explainable Reinforcement Learning","created":"2026-03-24","cited_by_count":1,"area":"deeprl"},{"id":"2105.07508","title":"Abstraction, Validation, and Generalization for Explainable Artificial Intelligence","created":"2021-05-16","cited_by_count":0,"area":null},{"id":"2201.07051","title":"System-Agnostic Meta-Learning for MDP-based Dynamic Scheduling via Descriptive Policy","created":"2022-01-18","cited_by_count":0,"area":null},{"id":"2209.09058","title":"Measuring Interventional Robustness in Reinforcement Learning","created":"2022-09-19","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":"2311.07797","title":"Explainable History Distillation by Marked Temporal Point Process","created":"2023-11-13","cited_by_count":0,"area":null},{"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":"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":"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":"2509.14925","title":"Self-Explaining Reinforcement Learning for Mobile Network Resource Allocation","created":"2025-09-18","cited_by_count":0,"area":"deeprl"},{"id":"2511.10409","title":"Explaining Decentralized Multi-Agent Reinforcement Learning Policies","created":"2025-11-13","cited_by_count":0,"area":null},{"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":"2512.09909","title":"STACHE: Local Black-Box Explanations for Reinforcement Learning Policies","created":"2025-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2606.25127","title":"Reward-Conditioned Attention: How Reward Design Shapes What Autonomous Driving Agents See","created":"2026-06-23","cited_by_count":0,"area":"driving"},{"id":"2607.11607","title":"Auditing the Risk Claims of Distributional Reinforcement Learning","created":"2026-07-13","cited_by_count":0,"area":"deeprl"},{"id":"2607.12861","title":"Unveiling Complex Collective Behaviors from Simple Rewards","created":"2026-07-14","cited_by_count":0,"area":"deeprl"},{"id":"2608.08497","title":"SocialFiVis: A Visual Analytics Sandbox for LLM-Grounded Multi-Agent Simulation in Social Finance","created":"2026-08-09","cited_by_count":0,"area":"agents"},{"id":"2609.05190","title":"The Mirror Agent Model: a Bayesian Architecture for Interpretable Agent Behavior","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}