{"total":106,"rows":[{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2105.07190","title":"A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts","created":"2021-05-15","cited_by_count":91,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46,"area":null},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"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":"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":"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":"2308.00143","title":"Formally Explaining Neural Networks within Reactive Systems","created":"2023-07-31","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":"2303.04926","title":"Automated Cyber Defence: A Review","created":"2023-03-08","cited_by_count":21,"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":"2306.09312","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2306.09318","title":"Inroads into Autonomous Network Defence using Explained Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2111.07505","title":"A Survey on AI Assurance","created":"2021-11-15","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":"2105.02658","title":"Explainable Autonomous Robots: A Survey and Perspective","created":"2021-05-06","cited_by_count":15,"area":null},{"id":"2111.06978","title":"RLOps: Development Life-cycle of Reinforcement Learning Aided Open RAN","created":"2021-11-12","cited_by_count":15,"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":"2503.23616","title":"Interpretable Machine Learning in Physics: A Review","created":"2025-03-30","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":"2108.08454","title":"Improving Human Sequential Decision-Making with Reinforcement Learning","created":"2021-08-19","cited_by_count":12,"area":null},{"id":"2206.04860","title":"Conformal Prediction Intervals for Markov Decision Process Trajectories","created":"2022-06-10","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":"2204.12568","title":"Toward Policy Explanations for Multi-Agent Reinforcement Learning","created":"2022-04-26","cited_by_count":11,"area":null},{"id":"2209.07225","title":"MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees","created":"2022-09-15","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":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2108.04526","title":"A Survey on Deep Reinforcement Learning for Data Processing and Analytics","created":"2021-08-10","cited_by_count":10,"area":null},{"id":"2305.10378","title":"Explainable Multi-Agent Reinforcement Learning for Temporal Queries","created":"2023-05-17","cited_by_count":9,"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":"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":"2305.04073","title":"Explaining RL Decisions with Trajectories","created":"2023-05-06","cited_by_count":7,"area":null},{"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":"2207.10163","title":"Constrained Prescriptive Trees via Column Generation","created":"2022-07-20","cited_by_count":6,"area":null},{"id":"2303.04475","title":"RACCER: Towards Reachable and Certain Counterfactual Explanations for Reinforcement Learning","created":"2023-03-08","cited_by_count":6,"area":null},{"id":"2502.02516","title":"Adaptive Exploration for Multi-Reward Multi-Policy Evaluation","created":"2025-02-04","cited_by_count":6,"area":null},{"id":"2502.14581","title":"A Statistical Case Against Empirical Human-AI Alignment","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2505.23860","title":"Quantum computing and artificial intelligence: status and perspectives","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2112.09462","title":"Contrastive Explanations for Comparing Preferences of Reinforcement Learning Agents","created":"2021-12-17","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":"2210.04723","title":"Experiential Explanations for Reinforcement Learning","created":"2022-10-10","cited_by_count":5,"area":null},{"id":"2210.05931","title":"Explaining Online Reinforcement Learning Decisions of Self-Adaptive Systems","created":"2022-10-12","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":"2304.11526","title":"How to Control Hydrodynamic Force on Fluidic Pinball via Deep Reinforcement Learning","created":"2023-04-23","cited_by_count":5,"area":null},{"id":"2305.10091","title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges","created":"2023-05-17","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":"2312.08466","title":"Efficiently Quantifying Individual Agent Importance in Cooperative MARL","created":"2023-12-13","cited_by_count":4,"area":null},{"id":"2502.03047","title":"Kozax: Flexible and Scalable Genetic Programming in JAX","created":"2025-02-05","cited_by_count":4,"area":null},{"id":"2504.05625","title":"Model-Agnostic Policy Explanations with Large Language Models","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2512.18564","title":"Vox Deorum: A Hybrid LLM Architecture for 4X / Grand Strategy Game AI -- Lessons from Civilization V","created":"2025-12-21","cited_by_count":4,"area":null},{"id":"2102.02639","title":"Improving Reinforcement Learning with Human Assistance: An Argument for Human Subject Studies with HIPPO Gym","created":"2021-02-02","cited_by_count":3,"area":null},{"id":"2106.14251","title":"Pairing Conceptual Modeling with Machine Learning","created":"2021-06-27","cited_by_count":3,"area":null},{"id":"2203.02776","title":"Boosting human decision-making with AI-generated decision aids","created":"2022-03-05","cited_by_count":3,"area":null},{"id":"2203.04303","title":"Policy Regularization for Legible Behavior","created":"2022-03-08","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":"2302.09688","title":"AutoDOViz: Human-Centered Automation for Decision Optimization","created":"2023-02-19","cited_by_count":3,"area":null},{"id":"2307.04098","title":"A User Study on Explainable Online Reinforcement Learning for Adaptive Systems","created":"2023-07-09","cited_by_count":3,"area":null},{"id":"2312.04216","title":"CODEX: A Cluster-Based Method for Explainable Reinforcement Learning","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2405.20705","title":"ADESSE: Advice Explanations in Complex Repeated Decision-Making Environments","created":"2024-05-31","cited_by_count":3,"area":null},{"id":"2410.03915","title":"Distribution Guided Active Feature Acquisition","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2202.07414","title":"Interpretable Reinforcement Learning with Multilevel Subgoal Discovery","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2207.06269","title":"Policy Optimization with Sparse Global Contrastive Explanations","created":"2022-07-13","cited_by_count":2,"area":null},{"id":"2208.08552","title":"A Framework for Understanding and Visualizing Strategies of RL Agents","created":"2022-08-17","cited_by_count":2,"area":null},{"id":"2208.08790","title":"Explainable Reinforcement Learning on Financial Stock Trading using SHAP","created":"2022-08-18","cited_by_count":2,"area":null},{"id":"2211.01036","title":"Explainable AI over the Internet of Things (IoT): Overview, State-of-the-Art and Future Directions","created":"2022-11-02","cited_by_count":2,"area":null},{"id":"2211.16566","title":"Relative Sparsity for Medical Decision Problems","created":"2022-11-29","cited_by_count":2,"area":null},{"id":"2307.01532","title":"Analyzing Intentional Behavior in Autonomous Agents under Uncertainty","created":"2023-07-04","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":"2312.08468","title":"On Diagnostics for Understanding Agent Training Behaviour in Cooperative MARL","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2201.08520","title":"Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning","created":"2022-01-21","cited_by_count":1,"area":null},{"id":"2209.03357","title":"Distilling Deep RL Models Into Interpretable Neuro-Fuzzy Systems","created":"2022-09-07","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":"2212.12743","title":"Automated Gadget Discovery in Science","created":"2022-12-24","cited_by_count":1,"area":null},{"id":"2309.14391","title":"An AI Chatbot for Explaining Deep Reinforcement Learning Decisions of Service-oriented Systems","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2312.08463","title":"How much can change in a year? Revisiting Evaluation in Multi-Agent Reinforcement Learning","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2407.00849","title":"Towards Understanding Sensitive and Decisive Patterns in Explainable AI: A Case Study of Model Interpretation in Geometric Deep Learning","created":"2024-06-30","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":"2511.15716","title":"MACIE: Multi-Agent Causal Intelligence Explainer for Collective Behavior Understanding","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2104.10492","title":"Skimming and Scanning for Untrimmed Video Action Recognition","created":"2021-04-21","cited_by_count":0,"area":null},{"id":"2109.08180","title":"Interpretable Local Tree Surrogate Policies","created":"2021-09-16","cited_by_count":0,"area":null},{"id":"2112.15034","title":"Self Reward Design with Fine-grained Interpretability","created":"2021-12-30","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":"2203.00822","title":"Keeping Minimal Experience to Achieve Efficient Interpretable Policy Distillation","created":"2022-03-02","cited_by_count":0,"area":null},{"id":"2205.13229","title":"Symbiotic Child Emotional Support with Social Robots and Temporal Knowledge Graphs","created":"2022-05-26","cited_by_count":0,"area":null},{"id":"2206.02039","title":"Beyond Value: CHECKLIST for Testing Inferences in Planning-Based RL","created":"2022-06-04","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":"2211.06376","title":"Global and Local Analysis of Interestingness for Competency-Aware Deep Reinforcement Learning","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2211.12930","title":"Introspection-based Explainable Reinforcement Learning in Episodic and Non-episodic Scenarios","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2211.16381","title":"Symmetry Detection in Trajectory Data for More Meaningful Reinforcement Learning Representations","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2304.09769","title":"End-to-End Policy Gradient Method for POMDPs and Explainable Agents","created":"2023-04-19","cited_by_count":0,"area":null},{"id":"2304.10375","title":"Interpretability for Conditional Coordinated Behavior in Multi-Agent Reinforcement Learning","created":"2023-04-20","cited_by_count":0,"area":null},{"id":"2307.08933","title":"IxDRL: A Novel Explainable Deep Reinforcement Learning Toolkit based on Analyses of Interestingness","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2309.06097","title":"Fidelity-Induced Interpretable Policy Extraction for Reinforcement Learning","created":"2023-09-12","cited_by_count":0,"area":null},{"id":"2311.04710","title":"The Quest for Content: A Survey of Search-Based Procedural Content Generation for Video Games","created":"2023-11-08","cited_by_count":0,"area":null},{"id":"2312.14196","title":"Optimizing Heat Alert Issuance with Reinforcement Learning","created":"2023-12-21","cited_by_count":0,"area":null},{"id":"2406.02765","title":"Discovering Continuous-Time Memory-Based Symbolic Policies using Genetic Programming","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2406.11850","title":"Closed-loop Teaching via Demonstrations to Improve Policy Transparency","created":"2024-04-01","cited_by_count":0,"area":null}],"next_cursor":"100"}