{"total":82,"rows":[{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174,"area":null},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"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":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"area":null},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37,"area":null},{"id":"2206.01078","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","created":"2022-06-02","cited_by_count":36,"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":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2103.00375","title":"Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control","created":"2021-02-28","cited_by_count":24,"area":"offlinerl"},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2111.04927","title":"Self-Interpretable Model with TransformationEquivariant Interpretation","created":"2021-11-09","cited_by_count":21,"area":null},{"id":"2305.19044","title":"Exploring the Promise and Limits of Real-Time Recurrent Learning","created":"2023-05-30","cited_by_count":19,"area":null},{"id":"2501.15638","title":"A Comprehensive Survey on Self-Interpretable Neural Networks","created":"2025-01-26","cited_by_count":18,"area":null},{"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":"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":"2208.03374","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","created":"2022-08-05","cited_by_count":13,"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":"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":"2112.04075","title":"Active Sensing for Communications by Learning","created":"2021-12-08","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":"2104.07750","title":"Joint Attention for Multi-Agent Coordination and Social Learning","created":"2021-04-15","cited_by_count":8,"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":"2104.09402","title":"Agent-Centric Representations for Multi-Agent Reinforcement Learning","created":"2021-04-19","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":"2201.00354","title":"Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference","created":"2022-01-02","cited_by_count":6,"area":null},{"id":"2202.02212","title":"Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model","created":"2022-02-04","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":"2412.05766","title":"Policy-shaped prediction: avoiding distractions in model-based reinforcement learning","created":"2024-12-08","cited_by_count":6,"area":"deeprl"},{"id":"2202.03597","title":"Local Explanations for Reinforcement Learning","created":"2022-02-08","cited_by_count":5,"area":null},{"id":"2211.03011","title":"On learning history based policies for controlling Markov decision processes","created":"2022-11-06","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":"2110.03760","title":"Design Strategy Network: A deep hierarchical framework to represent generative design strategies in complex action spaces","created":"2021-10-07","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":"2310.00229","title":"Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2201.08115","title":"Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning","created":"2022-01-20","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":"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":"2510.21809","title":"Embodied Navigation with Auxiliary Task of Action Description Prediction","created":"2025-10-21","cited_by_count":3,"area":"deeprl"},{"id":"2605.09965","title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2106.05139","title":"Pretrained Encoders are All You Need","created":"2021-06-09","cited_by_count":2,"area":null},{"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":"2211.06733","title":"Deep Reinforcement Learning with Vector Quantized Encoding","created":"2022-11-12","cited_by_count":2,"area":null},{"id":"2407.13518","title":"Model-based Policy Optimization using Symbolic World Model","created":"2024-07-18","cited_by_count":2,"area":"wm"},{"id":"2504.03024","title":"Deep Reinforcement Learning via Object-Centric Attention","created":"2025-04-03","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":"2102.11232","title":"Uncertainty Maximization in Partially Observable Domains: A Cognitive Perspective","created":"2021-02-22","cited_by_count":1,"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":"2201.08520","title":"Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning","created":"2022-01-21","cited_by_count":1,"area":null},{"id":"2205.08926","title":"Generating Explanations from Deep Reinforcement Learning Using Episodic Memory","created":"2022-05-18","cited_by_count":1,"area":null},{"id":"2209.07043","title":"Towards self-attention based visual navigation in the real world","created":"2022-09-15","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":"2301.03043","title":"XDQN: Inherently Interpretable DQN through Mimicking","created":"2023-01-08","cited_by_count":1,"area":null},{"id":"2303.07925","title":"Deep incremental learning models for financial temporal tabular datasets with distribution shifts","created":"2023-03-14","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":"2409.17411","title":"Enhancing Interpretability in Deep Reinforcement Learning through Semantic Clustering","created":"2024-09-25","cited_by_count":1,"area":"deeprl"},{"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":"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"},{"id":"2112.08369","title":"Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning","created":"2021-12-15","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":"2207.04969","title":"From Correlation to Causation: Formalizing Interpretable Machine Learning as a Statistical Process","created":"2022-07-11","cited_by_count":0,"area":null},{"id":"2301.11168","title":"Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2306.13879","title":"Action Q-Transformer: Visual Explanation in Deep Reinforcement Learning with Encoder-Decoder Model using Action Query","created":"2023-06-24","cited_by_count":0,"area":null},{"id":"2310.00489","title":"Interpretable Imitation Learning with Dynamic Causal Relations","created":"2023-09-30","cited_by_count":0,"area":"offlinerl"},{"id":"2310.03161","title":"Neural architecture impact on identifying temporally extended Reinforcement Learning tasks","created":"2023-10-04","cited_by_count":0,"area":null},{"id":"2406.14214","title":"REVEAL-IT: REinforcement learning with Visibility of Evolving Agent poLicy for InTerpretability","created":"2024-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2502.15512","title":"SALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learning","created":"2025-02-21","cited_by_count":0,"area":"deeprl"},{"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":"2505.11153","title":"Bi-directional Recurrence Improves Transformer in Partially Observable Markov Decision Processes","created":"2025-05-16","cited_by_count":0,"area":"deeprl"},{"id":"2506.00691","title":"Optimizing Sensory Neurons: Nonlinear Attention Mechanisms for Accelerated Convergence in Permutation-Invariant Neural Networks for Reinforcement Learning","created":"2025-05-31","cited_by_count":0,"area":"deeprl"},{"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":"2512.14726","title":"Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning","created":"2025-12-09","cited_by_count":0,"area":"offlinerl"},{"id":"2603.27971","title":"Principal Prototype Analysis on Manifold for Interpretable Reinforcement Learning","created":"2026-03-30","cited_by_count":0,"area":"alignment"},{"id":"2607.03703","title":"Explainable Reinforcement Learning for Adaptive Traffic Signal Control","created":"2026-07-04","cited_by_count":0,"area":"deeprl"},{"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}