{"total":193,"rows":[{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2402.12275","title":"WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment","created":"2024-02-19","cited_by_count":107,"area":"wm"},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2106.13906","title":"Compositional Reinforcement Learning from Logical Specifications","created":"2021-06-25","cited_by_count":67,"area":null},{"id":"2108.13643","title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies","created":"2021-08-31","cited_by_count":59,"area":null},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"id":"2102.01168","title":"Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges","created":"2021-01-27","cited_by_count":50,"area":null},{"id":"2306.01439","title":"Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction","created":"2023-06-02","cited_by_count":46,"area":null},{"id":"2405.15383","title":"Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search","created":"2024-05-24","cited_by_count":40,"area":"wm"},{"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":"2301.09937","title":"Explainable Deep Reinforcement Learning: State of the Art and Challenges","created":"2023-01-24","cited_by_count":33,"area":null},{"id":"2402.19299","title":"RL-GPT: Integrating Reinforcement Learning and Code-as-policy","created":"2024-02-29","cited_by_count":32,"area":null},{"id":"2202.08434","title":"A Survey of Explainable Reinforcement Learning","created":"2022-02-17","cited_by_count":31,"area":null},{"id":"1904.06317","title":"Few-Shot Bayesian Imitation Learning with Logical Program Policies","created":"2019-04-12","cited_by_count":30,"area":"offlinerl"},{"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":"2309.01038","title":"Neurosymbolic Reinforcement Learning and Planning: A Survey","created":"2023-09-02","cited_by_count":24,"area":null},{"id":"2401.05821","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","created":"2024-01-11","cited_by_count":23,"area":"deeprl"},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21,"area":null},{"id":"2104.04515","title":"Connecting Attributions and QA Model Behavior on Realistic Counterfactuals","created":"2021-04-09","cited_by_count":20,"area":null},{"id":"2301.12950","title":"Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs","created":"2023-01-30","cited_by_count":20,"area":null},{"id":"2405.14956","title":"Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning","created":"2024-05-23","cited_by_count":18,"area":"deeprl"},{"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":"2112.08907","title":"Inherently Explainable Reinforcement Learning in Natural Language","created":"2021-12-16","cited_by_count":16,"area":null},{"id":"2205.13728","title":"GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis","created":"2022-05-27","cited_by_count":16,"area":null},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2404.06492","title":"Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective","created":"2024-04-09","cited_by_count":16,"area":"deeprl"},{"id":"2105.02658","title":"Explainable Autonomous Robots: A Survey and Perspective","created":"2021-05-06","cited_by_count":15,"area":null},{"id":"2405.13863","title":"Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning","created":"2024-05-22","cited_by_count":15,"area":"deeprl"},{"id":"2203.08057","title":"POETREE: Interpretable Policy Learning with Adaptive Decision Trees","created":"2022-03-15","cited_by_count":14,"area":null},{"id":"2205.10032","title":"Survey on Fair Reinforcement Learning: Theory and Practice","created":"2022-05-20","cited_by_count":14,"area":null},{"id":"2410.11689","title":"BlendRL: A Framework for Merging Symbolic and Neural Policy Learning","created":"2024-10-15","cited_by_count":14,"area":"lr"},{"id":"2101.03238","title":"Neurosymbolic Transformers for Multi-Agent Communication","created":"2021-01-05","cited_by_count":13,"area":null},{"id":"2104.02938","title":"Deep Interpretable Models of Theory of Mind","created":"2021-04-07","cited_by_count":13,"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":"2405.16450","title":"Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search","created":"2024-05-26","cited_by_count":13,"area":null},{"id":"2108.08454","title":"Improving Human Sequential Decision-Making with Reinforcement Learning","created":"2021-08-19","cited_by_count":12,"area":null},{"id":"2203.11547","title":"Explainability in reinforcement learning: perspective and position","created":"2022-03-22","cited_by_count":11,"area":null},{"id":"2203.11912","title":"What can we Learn Even From the Weakest? Learning Sketches for Programmatic Strategies","created":"2022-03-22","cited_by_count":11,"area":"offlinerl"},{"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":"2302.10809","title":"Causal Explanations for Sequential Decision-Making in Multi-Agent Systems","created":"2023-02-21","cited_by_count":10,"area":null},{"id":"2309.14972","title":"Improving Unsupervised Visual Program Inference with Code Rewriting Families","created":"2023-09-26","cited_by_count":10,"area":null},{"id":"2311.02104","title":"Efficient Symbolic Policy Learning with Differentiable Symbolic Expression","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"1902.10657","title":"From explanation to synthesis: Compositional program induction for learning from demonstration","created":"2019-02-27","cited_by_count":9,"area":"offlinerl"},{"id":"2103.08228","title":"Learning Symbolic Rules for Interpretable Deep Reinforcement Learning","created":"2021-03-15","cited_by_count":9,"area":null},{"id":"2112.08438","title":"Programmatic Reward Design by Example","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2204.09772","title":"A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines","created":"2022-04-20","cited_by_count":9,"area":"offlinerl"},{"id":"2204.12822","title":"A Survey on XAI for 5G and Beyond Security: Technical Aspects, Challenges and Research Directions","created":"2022-04-27","cited_by_count":9,"area":null},{"id":"2212.14849","title":"Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search","created":"2022-12-30","cited_by_count":9,"area":null},{"id":"2308.07795","title":"Learning to Identify Critical States for Reinforcement Learning from Videos","created":"2023-08-15","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":"2102.11137","title":"Program Synthesis Guided Reinforcement Learning for Partially Observed Environments","created":"2021-02-22","cited_by_count":8,"area":null},{"id":"2106.11417","title":"Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming","created":"2021-06-21","cited_by_count":8,"area":null},{"id":"2107.13132","title":"Unsupervised Learning of Neurosymbolic Encoders","created":"2021-07-28","cited_by_count":8,"area":null},{"id":"2205.07394","title":"Sibyl: Adaptive and Extensible Data Placement in Hybrid Storage Systems Using Online Reinforcement Learning","created":"2022-05-15","cited_by_count":8,"area":null},{"id":"2307.04893","title":"Choosing Well Your Opponents: How to Guide the Synthesis of Programmatic Strategies","created":"2023-07-10","cited_by_count":8,"area":null},{"id":"2508.05433","title":"Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policies","created":"2025-08-07","cited_by_count":8,"area":"mllm"},{"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":"2203.13553","title":"Preprocessing Reward Functions for Interpretability","created":"2022-03-25","cited_by_count":7,"area":"alignment"},{"id":"2210.05050","title":"Neurosymbolic Programming for Science","created":"2022-10-10","cited_by_count":7,"area":null},{"id":"2303.06018","title":"Hierarchical Neural Program Synthesis","created":"2023-03-09","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":"2310.04327","title":"Program Synthesis with Best-First Bottom-Up Search","created":"2023-10-06","cited_by_count":7,"area":null},{"id":"2105.07099","title":"Feature-Based Interpretable Reinforcement Learning based on State-Transition Models","created":"2021-05-14","cited_by_count":6,"area":null},{"id":"2111.15186","title":"Automatic Synthesis of Diverse Weak Supervision Sources for Behavior Analysis","created":"2021-11-30","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":"2408.09135","title":"Vanilla Gradient Descent for Oblique Decision Trees","created":"2024-08-17","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":"2112.04698","title":"Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges","created":"2021-12-09","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":"2211.05551","title":"Causal Counterfactuals for Improving the Robustness of Reinforcement Learning","created":"2022-11-02","cited_by_count":5,"area":null},{"id":"2304.12090","title":"Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2309.03651","title":"Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments","created":"2023-09-07","cited_by_count":5,"area":null},{"id":"2405.05431","title":"Searching for Programmatic Policies in Semantic Spaces","created":"2024-05-08","cited_by_count":5,"area":null},{"id":"2406.06107","title":"EXPIL: Explanatory Predicate Invention for Learning in Games","created":"2024-06-10","cited_by_count":5,"area":"deeprl"},{"id":"2407.15786","title":"LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learning","created":"2024-07-22","cited_by_count":5,"area":"lr"},{"id":"2408.08761","title":"Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization","created":"2024-08-16","cited_by_count":5,"area":"deeprl"},{"id":"2411.11761","title":"Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework","created":"2024-11-18","cited_by_count":5,"area":"agents"},{"id":"2412.04057","title":"From Code to Play: Benchmarking Program Search for Games Using Large Language Models","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2103.03938","title":"Causal Analysis of Agent Behavior for AI Safety","created":"2021-03-05","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":"2206.04266","title":"There is no Accuracy-Interpretability Tradeoff in Reinforcement Learning for Mazes","created":"2022-06-09","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":"2303.10382","title":"Interpretable Reinforcement Learning via Neural Additive Models for Inventory Management","created":"2023-03-18","cited_by_count":4,"area":null},{"id":"2310.07918","title":"Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning","created":"2023-10-11","cited_by_count":4,"area":"offlinerl"},{"id":"2310.19137","title":"Automaton Distillation: Neuro-Symbolic Transfer Learning for Deep Reinforcement Learning","created":"2023-10-29","cited_by_count":4,"area":null},{"id":"2501.03888","title":"Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policies","created":"2025-01-07","cited_by_count":4,"area":"deeprl"},{"id":"2504.05625","title":"Model-Agnostic Policy Explanations with Large Language Models","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2506.06981","title":"Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments","created":"2025-06-08","cited_by_count":4,"area":"deeprl"},{"id":"2601.06845","title":"Code Evolution for Control: Synthesizing Policies via LLM-Driven Evolutionary Search","created":"2026-01-11","cited_by_count":4,"area":null},{"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":"2101.09571","title":"BF++: a language for general-purpose program synthesis","created":"2021-01-23","cited_by_count":3,"area":null},{"id":"2106.06931","title":"Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learning","created":"2021-06-13","cited_by_count":3,"area":null},{"id":"2112.06148","title":"Programming with Neural Surrogates of Programs","created":"2021-12-12","cited_by_count":3,"area":null},{"id":"2206.09046","title":"Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis","created":"2022-06-17","cited_by_count":3,"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":"2303.01440","title":"Programmatic Imitation Learning from Unlabeled and Noisy Demonstrations","created":"2023-03-02","cited_by_count":3,"area":"offlinerl"}],"next_cursor":"100"}