{"total":141,"rows":[{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410,"area":null},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260,"area":"offlinerl"},{"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":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2106.09678","title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies","created":"2021-06-17","cited_by_count":43,"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":"2109.09904","title":"Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems","created":"2021-09-21","cited_by_count":36,"area":null},{"id":"2102.05714","title":"Domain Adaptation In Reinforcement Learning Via Latent Unified State Representation","created":"2021-02-10","cited_by_count":35,"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":"2102.13045","title":"Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods","created":"2021-02-25","cited_by_count":31,"area":null},{"id":"2202.08434","title":"A Survey of Explainable Reinforcement Learning","created":"2022-02-17","cited_by_count":31,"area":null},{"id":"2110.01307","title":"Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning with Shapley Values","created":"2021-10-04","cited_by_count":25,"area":null},{"id":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2412.01034","title":"Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control","created":"2024-12-02","cited_by_count":25,"area":"vla"},{"id":"2108.09003","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","created":"2021-08-20","cited_by_count":24,"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":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2111.10009","title":"ExoMiner: A Highly Accurate and Explainable Deep Learning Classifier that Validates 301 New Exoplanets","created":"2021-11-19","cited_by_count":17,"area":null},{"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":"2106.10938","title":"A Game-Theoretic Taxonomy of Visual Concepts in DNNs","created":"2021-06-21","cited_by_count":16,"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":"2107.09540","title":"Critic Guided Segmentation of Rewarding Objects in First-Person Views","created":"2021-07-20","cited_by_count":12,"area":"offlinerl"},{"id":"2404.08828","title":"Hindsight PRIORs for Reward Learning from Human Preferences","created":"2024-04-12","cited_by_count":12,"area":"alignment"},{"id":"2505.15304","title":"Saliency-Aware Quantized Imitation Learning for Efficient Robotic Control","created":"2025-05-21","cited_by_count":12,"area":"vla"},{"id":"2203.11547","title":"Explainability in reinforcement learning: perspective and position","created":"2022-03-22","cited_by_count":11,"area":null},{"id":"2209.12006","title":"Explainable Reinforcement Learning via Model Transforms","created":"2022-09-24","cited_by_count":11,"area":null},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11,"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":"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":"2107.13668","title":"Discovering User-Interpretable Capabilities of Black-Box Planning Agents","created":"2021-07-28","cited_by_count":10,"area":null},{"id":"2603.18202","title":"R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation","created":"2026-03-18","cited_by_count":10,"area":"wm"},{"id":"2102.09677","title":"Training a Resilient Q-Network against Observational Interference","created":"2021-02-18","cited_by_count":9,"area":null},{"id":"2103.04067","title":"Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning","created":"2021-03-06","cited_by_count":9,"area":null},{"id":"2103.08228","title":"Learning Symbolic Rules for Interpretable Deep Reinforcement Learning","created":"2021-03-15","cited_by_count":9,"area":null},{"id":"2110.03184","title":"Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Model","created":"2021-10-07","cited_by_count":9,"area":null},{"id":"2110.12985","title":"Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2111.10518","title":"Towards Safe, Explainable, and Regulated Autonomous Driving","created":"2021-11-20","cited_by_count":7,"area":"driving"},{"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":"2304.12958","title":"A Closer Look at Reward Decomposition for High-Level Robotic Explanations","created":"2023-04-25","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":"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":"2510.21110","title":"Confounding Robust Deep Reinforcement Learning: A Causal Approach","created":"2025-10-24","cited_by_count":7,"area":"deeprl"},{"id":"1907.03976","title":"Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations","created":"2019-07-09","cited_by_count":6,"area":"offlinerl"},{"id":"2102.03064","title":"\"I Don't Think So\": Summarizing Policy Disagreements for Agent Comparison","created":"2021-02-05","cited_by_count":6,"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":"2306.04806","title":"Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings (Extended Version)","created":"2023-06-07","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":"2112.09462","title":"Contrastive Explanations for Comparing Preferences of Reinforcement Learning Agents","created":"2021-12-17","cited_by_count":5,"area":null},{"id":"2202.03597","title":"Local Explanations for Reinforcement Learning","created":"2022-02-08","cited_by_count":5,"area":null},{"id":"2207.03214","title":"Evaluating Human-like Explanations for Robot Actions in Reinforcement Learning Scenarios","created":"2022-07-07","cited_by_count":5,"area":null},{"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":"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":"2211.03162","title":"ProtoX: Explaining a Reinforcement Learning Agent via Prototyping","created":"2022-11-06","cited_by_count":4,"area":null},{"id":"2211.16221","title":"Configurable Agent With Reward As Input: A Play-Style Continuum Generation","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2303.02814","title":"Visual Analytics of Neuron Vulnerability to Adversarial Attacks on Convolutional Neural Networks","created":"2023-03-06","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":"2602.05048","title":"MINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active Elicitation","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2211.06665","title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2302.09688","title":"AutoDOViz: Human-Centered Automation for Decision Optimization","created":"2023-02-19","cited_by_count":3,"area":null},{"id":"2309.01458","title":"Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning","created":"2023-09-04","cited_by_count":3,"area":null},{"id":"2309.04707","title":"Advantage Actor-Critic with Reasoner: Explaining the Agent's Behavior from an Exploratory Perspective","created":"2023-09-09","cited_by_count":3,"area":null},{"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":"2109.13978","title":"Identifying Reasoning Flaws in Planning-Based RL Using Tree Explanations","created":"2021-09-28","cited_by_count":2,"area":null},{"id":"2111.08094","title":"LIMEcraft: Handcrafted superpixel selection and inspection for Visual eXplanations","created":"2021-11-15","cited_by_count":2,"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":"2302.08734","title":"A State Augmentation based approach to Reinforcement Learning from Human Preferences","created":"2023-02-17","cited_by_count":2,"area":"alignment"},{"id":"2307.13192","title":"Counterfactual Explanation Policies in RL","created":"2023-07-25","cited_by_count":2,"area":null},{"id":"2401.00104","title":"Causal State Distillation for Explainable Reinforcement Learning","created":"2023-12-30","cited_by_count":2,"area":null},{"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":"2408.03884","title":"Quantum Computing and Neuromorphic Computing for Safe, Reliable, and explainable Multi-Agent Reinforcement Learning: Optimal Control in Autonomous Robotics","created":"2024-07-29","cited_by_count":2,"area":null},{"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":"2504.05950","title":"AEGIS: Human Attention-based Explainable Guidance for Intelligent Vehicle Systems","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2001.01683","title":"Deep Innovation Protection: Confronting the Credit Assignment Problem in Training Heterogeneous Neural Architectures","created":"2019-12-29","cited_by_count":1,"area":"wm"},{"id":"2205.08926","title":"Generating Explanations from Deep Reinforcement Learning Using Episodic Memory","created":"2022-05-18","cited_by_count":1,"area":null},{"id":"2209.03207","title":"Concept-modulated model-based offline reinforcement learning for rapid generalization","created":"2022-09-07","cited_by_count":1,"area":"offlinerl"},{"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":"2302.09318","title":"Effective Multimodal Reinforcement Learning with Modality Alignment and Importance Enhancement","created":"2023-02-18","cited_by_count":1,"area":null},{"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":"2408.14649","title":"Bidirectional Emergent Language in Situated Environments","created":"2024-08-26","cited_by_count":1,"area":null},{"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":"2503.16724","title":"Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models","created":"2025-03-20","cited_by_count":1,"area":"mllm"},{"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":"2511.15716","title":"MACIE: Multi-Agent Causal Intelligence Explainer for Collective Behavior Understanding","created":"2025-11-11","cited_by_count":1,"area":null},{"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"}],"next_cursor":"100"}