{"total":73,"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":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123,"area":null},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73,"area":null},{"id":"2312.01072","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","created":"2023-12-02","cited_by_count":59,"area":null},{"id":"2409.18121","title":"Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction","created":"2024-09-26","cited_by_count":54,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","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":"2107.12544","title":"Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning","created":"2021-07-27","cited_by_count":43,"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":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2102.09117","title":"Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking","created":"2021-02-18","cited_by_count":35,"area":null},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31,"area":"wm"},{"id":"2206.07922","title":"Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications","created":"2022-06-16","cited_by_count":30,"area":null},{"id":"2203.05960","title":"Policy Architectures for Compositional Generalization in Control","created":"2022-03-10","cited_by_count":23,"area":null},{"id":"2306.02500","title":"Systematic Visual Reasoning through Object-Centric Relational Abstraction","created":"2023-06-04","cited_by_count":20,"area":"lr"},{"id":"2110.05734","title":"Learning Efficient Multi-Agent Cooperative Visual Exploration","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2201.13388","title":"Compositional Multi-Object Reinforcement Learning with Linear Relation Networks","created":"2022-01-31","cited_by_count":19,"area":null},{"id":"2301.03398","title":"Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration","created":"2023-01-09","cited_by_count":18,"area":null},{"id":"2105.12899","title":"Learning to Optimize Industry-Scale Dynamic Pickup and Delivery Problems","created":"2021-05-27","cited_by_count":15,"area":null},{"id":"2301.12962","title":"Hierarchical Imitation Learning with Vector Quantized Models","created":"2023-01-30","cited_by_count":15,"area":"offlinerl"},{"id":"2304.08349","title":"Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach","created":"2023-04-17","cited_by_count":15,"area":null},{"id":"2209.11553","title":"On Efficient Reinforcement Learning for Full-length Game of StarCraft II","created":"2022-09-23","cited_by_count":14,"area":null},{"id":"2212.04821","title":"PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data","created":"2022-12-08","cited_by_count":14,"area":null},{"id":"2407.15589","title":"Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13,"area":null},{"id":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2103.17232","title":"Neuro-Symbolic Constraint Programming for Structured Prediction","created":"2021-03-31","cited_by_count":11,"area":null},{"id":"2203.11547","title":"Explainability in reinforcement learning: perspective and position","created":"2022-03-22","cited_by_count":11,"area":null},{"id":"2209.08660","title":"Learn the Time to Learn: Replay Scheduling in Continual Learning","created":"2022-09-18","cited_by_count":11,"area":null},{"id":"2108.13696","title":"Phy-Q as a measure for physical reasoning intelligence","created":"2021-08-31","cited_by_count":10,"area":null},{"id":"2406.05064","title":"Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning","created":"2024-06-07","cited_by_count":10,"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":"2312.10728","title":"Benchmarks for Physical Reasoning AI","created":"2023-12-17","cited_by_count":8,"area":null},{"id":"2106.02204","title":"Detecting and Adapting to Novelty in Games","created":"2021-06-04","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":"2111.14598","title":"Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning","created":"2021-11-29","cited_by_count":6,"area":null},{"id":"2310.12819","title":"Hybrid Search for Efficient Planning with Completeness Guarantees","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2106.14587","title":"Topos and Stacks of Deep Neural Networks","created":"2021-06-28","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":"2402.02701","title":"Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence","created":"2024-02-05","cited_by_count":5,"area":"deeprl"},{"id":"2408.05861","title":"Temporal Knowledge-Graph Memory in a Partially Observable Environment","created":"2024-08-11","cited_by_count":5,"area":null},{"id":"2510.26270","title":"Graph-Enhanced Policy Optimization in LLM Agent Training","created":"2025-10-30","cited_by_count":5,"area":"agents"},{"id":"2207.06105","title":"GriddlyJS: A Web IDE for Reinforcement Learning","created":"2022-07-13","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":"2503.09270","title":"Rule-Guided Reinforcement Learning Policy Evaluation and Improvement","created":"2025-03-12","cited_by_count":4,"area":"deeprl"},{"id":"2106.05907","title":"DAIR: Disentangled Attention Intrinsic Regularization for Safe and Efficient Bimanual Manipulation","created":"2021-06-10","cited_by_count":3,"area":null},{"id":"2112.14843","title":"A Graph Attention Learning Approach to Antenna Tilt Optimization","created":"2021-12-27","cited_by_count":3,"area":null},{"id":"2412.04752","title":"Graph Neural Network Based Action Ranking for Planning","created":"2024-12-06","cited_by_count":3,"area":null},{"id":"2508.12480","title":"The Yokai Learning Environment: Tracking Beliefs Over Space and Time","created":"2025-08-17","cited_by_count":3,"area":null},{"id":"2102.04220","title":"Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning","created":"2021-02-08","cited_by_count":2,"area":null},{"id":"2105.12254","title":"Interpretable UAV Collision Avoidance using Deep Reinforcement Learning","created":"2021-05-25","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":"2301.09770","title":"Language-guided Task Adaptation for Imitation Learning","created":"2023-01-24","cited_by_count":2,"area":"offlinerl"},{"id":"2202.00531","title":"PRIMA: Planner-Reasoner Inside a Multi-task Reasoning Agent","created":"2022-02-01","cited_by_count":1,"area":null},{"id":"2212.11030","title":"Deep set conditioned latent representations for action recognition","created":"2022-12-21","cited_by_count":1,"area":null},{"id":"2306.05727","title":"The Role of Diverse Replay for Generalisation in Reinforcement Learning","created":"2023-06-09","cited_by_count":1,"area":null},{"id":"2310.09383","title":"Integrating Symbolic Reasoning into Neural Generative Models for Design Generation","created":"2023-10-13","cited_by_count":1,"area":"lr"},{"id":"2401.05822","title":"Towards Goal-Oriented Agents for Evolving Problems Observed via Conversation","created":"2024-01-11","cited_by_count":1,"area":null},{"id":"2406.11249","title":"Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2410.03565","title":"Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2506.07255","title":"Subgoal-Guided Policy Heuristic Search with Learned Subgoals","created":"2025-06-08","cited_by_count":1,"area":null},{"id":"2109.12691","title":"Applying supervised and reinforcement learning methods to create neural-network-based agents for playing StarCraft II","created":"2021-09-26","cited_by_count":0,"area":null},{"id":"2204.05141","title":"Learning Object-Centered Autotelic Behaviors with Graph Neural Networks","created":"2022-04-11","cited_by_count":0,"area":null},{"id":"2206.06346","title":"Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens","created":"2022-06-13","cited_by_count":0,"area":null},{"id":"2312.11138","title":"Rapid Open-World Adaptation by Adaptation Principles Learning","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2402.15561","title":"Fair Multivariate Adaptive Regression Splines for Ensuring Equity and Transparency","created":"2024-02-23","cited_by_count":0,"area":null},{"id":"2406.08069","title":"Explore-Go: Leveraging Exploration for Generalisation in Deep Reinforcement Learning","created":"2024-06-12","cited_by_count":0,"area":"deeprl"},{"id":"2411.00382","title":"Communication Learning in Multi-Agent Systems from Graph Modeling Perspective","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2505.12109","title":"SAINT: Attention-Based Policies for Discrete Combinatorial Action Spaces","created":"2025-05-17","cited_by_count":0,"area":"deeprl"},{"id":"2602.19956","title":"Sparse Masked Attention Policies for Reliable Generalization","created":"2026-02-23","cited_by_count":0,"area":"deeprl"},{"id":"2604.08355","title":"ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2606.14892","title":"Relational Structural Causal Models","created":"2026-06-12","cited_by_count":0,"area":null}],"next_cursor":null}