{"total":172,"rows":[{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141,"area":null},{"id":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2108.10573","title":"The staircase property: How hierarchical structure can guide deep learning","created":"2021-08-24","cited_by_count":62,"area":null},{"id":"2312.09238","title":"Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft","created":"2023-12-14","cited_by_count":61,"area":null},{"id":"2102.07952","title":"A Survey of Machine Learning for Computer Architecture and Systems","created":"2021-02-16","cited_by_count":53,"area":null},{"id":"2309.00987","title":"Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation","created":"2023-09-02","cited_by_count":49,"area":null},{"id":"2110.13625","title":"Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning","created":"2021-10-26","cited_by_count":47,"area":null},{"id":"2111.07999","title":"Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization","created":"2021-11-15","cited_by_count":46,"area":null},{"id":"2208.09515","title":"Spectral Decomposition Representation for Reinforcement Learning","created":"2022-08-19","cited_by_count":36,"area":null},{"id":"2206.10607","title":"MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer","created":"2022-06-20","cited_by_count":34,"area":null},{"id":"2103.15793","title":"LASER: Learning a Latent Action Space for Efficient Reinforcement Learning","created":"2021-03-29","cited_by_count":32,"area":null},{"id":"2102.06741","title":"Discovery of Options via Meta-Learned Subgoals","created":"2021-02-12","cited_by_count":27,"area":null},{"id":"2111.03189","title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning","created":"2021-11-04","cited_by_count":26,"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":"2102.07247","title":"Reinforcement Learning for IoT Security: A Comprehensive Survey","created":"2021-02-14","cited_by_count":23,"area":null},{"id":"2203.08994","title":"AI Autonomy : Self-Initiated Open-World Continual Learning and Adaptation","created":"2022-03-17","cited_by_count":23,"area":null},{"id":"2202.02886","title":"Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity","created":"2022-02-06","cited_by_count":22,"area":null},{"id":"2212.04590","title":"Learning Options via Compression","created":"2022-12-08","cited_by_count":22,"area":null},{"id":"2109.03540","title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions","created":"2021-09-08","cited_by_count":21,"area":null},{"id":"2208.08731","title":"Intelligent problem-solving as integrated hierarchical reinforcement learning","created":"2022-08-18","cited_by_count":21,"area":null},{"id":"2307.10710","title":"Reparameterized Policy Learning for Multimodal Trajectory Optimization","created":"2023-07-20","cited_by_count":20,"area":null},{"id":"2103.07607","title":"Solving Compositional Reinforcement Learning Problems via Task Reduction","created":"2021-03-13","cited_by_count":19,"area":null},{"id":"2205.14205","title":"ALMA: Hierarchical Learning for Composite Multi-Agent Tasks","created":"2022-05-27","cited_by_count":18,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2105.14750","title":"Active Hierarchical Exploration with Stable Subgoal Representation Learning","created":"2021-05-31","cited_by_count":17,"area":null},{"id":"2107.03961","title":"Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2112.07640","title":"How and Why to Manipulate Your Own Agent: On the Incentives of Users of Learning Agents","created":"2021-12-14","cited_by_count":17,"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":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2206.14302","title":"Reinforcement Learning in Medical Image Analysis: Concepts, Applications, Challenges, and Future Directions","created":"2022-06-28","cited_by_count":16,"area":null},{"id":"2310.02264","title":"Generalizable Long-Horizon Manipulations with Large Language Models","created":"2023-10-03","cited_by_count":16,"area":null},{"id":"2210.12485","title":"DANLI: Deliberative Agent for Following Natural Language Instructions","created":"2022-10-22","cited_by_count":15,"area":null},{"id":"2512.18623","title":"LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction","created":"2025-12-21","cited_by_count":15,"area":null},{"id":"2502.05454","title":"Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following","created":"2025-02-08","cited_by_count":14,"area":null},{"id":"2106.05864","title":"Verifiable and Compositional Reinforcement Learning Systems","created":"2021-06-07","cited_by_count":13,"area":null},{"id":"2107.05825","title":"Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2206.08736","title":"Generalised Policy Improvement with Geometric Policy Composition","created":"2022-06-17","cited_by_count":13,"area":null},{"id":"2410.18076","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","created":"2024-10-23","cited_by_count":13,"area":null},{"id":"2110.08258","title":"A Framework for Learning to Request Rich and Contextually Useful Information from Humans","created":"2021-10-14","cited_by_count":12,"area":null},{"id":"2203.14852","title":"Learning Sketches for Decomposing Planning Problems into Subproblems of Bounded Width: Extended Version","created":"2022-03-28","cited_by_count":12,"area":null},{"id":"2204.11833","title":"Joint Learning of Reward Machines and Policies in Environments with Partially Known Semantics","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2109.09968","title":"Generalization in Text-based Games via Hierarchical Reinforcement Learning","created":"2021-09-21","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":"2207.05683","title":"Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL","created":"2022-06-01","cited_by_count":11,"area":null},{"id":"2211.00247","title":"Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning","created":"2022-11-01","cited_by_count":11,"area":null},{"id":"2311.02129","title":"Hierarchical Reinforcement Learning for Power Network Topology Control","created":"2023-11-03","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":"2111.00213","title":"Adjacency constraint for efficient hierarchical reinforcement learning","created":"2021-10-30","cited_by_count":10,"area":null},{"id":"2112.02862","title":"SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation","created":"2021-12-06","cited_by_count":10,"area":null},{"id":"2203.11176","title":"One After Another: Learning Incremental Skills for a Changing World","created":"2022-03-21","cited_by_count":10,"area":null},{"id":"2204.09597","title":"Perceiving the World: Question-guided Reinforcement Learning for Text-based Games","created":"2022-03-20","cited_by_count":10,"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":"2402.07069","title":"Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machine","created":"2024-02-11","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":"2109.09876","title":"Context-Specific Representation Abstraction for Deep Option Learning","created":"2021-09-20","cited_by_count":8,"area":null},{"id":"2110.14541","title":"Deep Reinforcement Learning for Simultaneous Sensing and Channel Access in Cognitive Networks","created":"2021-10-24","cited_by_count":8,"area":null},{"id":"2201.02628","title":"Attention Option-Critic","created":"2022-01-07","cited_by_count":8,"area":null},{"id":"2201.09635","title":"State-Conditioned Adversarial Subgoal Generation","created":"2022-01-24","cited_by_count":8,"area":null},{"id":"2211.09382","title":"Planning Irregular Object Packing via Hierarchical Reinforcement Learning","created":"2022-11-17","cited_by_count":8,"area":null},{"id":"2301.00005","title":"Intrinsic Motivation in Dynamical Control Systems","created":"2022-12-29","cited_by_count":8,"area":null},{"id":"2306.06253","title":"Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2405.15194","title":"Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning","created":"2024-05-24","cited_by_count":8,"area":null},{"id":"2103.01350","title":"Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph","created":"2021-03-01","cited_by_count":7,"area":null},{"id":"2105.09992","title":"Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness","created":"2021-05-20","cited_by_count":7,"area":null},{"id":"2106.00897","title":"Solving Large-Scale Extensive-Form Network Security Games via Neural Fictitious Self-Play","created":"2021-06-02","cited_by_count":7,"area":null},{"id":"2110.14221","title":"Learning Diverse Policies in MOBA Games via Macro-Goals","created":"2021-10-27","cited_by_count":7,"area":null},{"id":"2201.00006","title":"Leveraging Queue Length and Attention Mechanisms for Enhanced Traffic Signal Control Optimization","created":"2021-12-30","cited_by_count":7,"area":null},{"id":"2207.11584","title":"Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning","created":"2022-07-23","cited_by_count":7,"area":null},{"id":"2110.04357","title":"Training Transition Policies via Distribution Matching for Complex Tasks","created":"2021-10-08","cited_by_count":6,"area":null},{"id":"2302.04094","title":"Learning Graph-Enhanced Commander-Executor for Multi-Agent Navigation","created":"2023-02-08","cited_by_count":6,"area":null},{"id":"2309.07675","title":"Goal Space Abstraction in Hierarchical Reinforcement Learning via Set-Based Reachability Analysis","created":"2023-09-14","cited_by_count":6,"area":null},{"id":"2312.11364","title":"Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structure","created":"2023-12-18","cited_by_count":6,"area":null},{"id":"2106.13935","title":"Discovering Generalizable Skills via Automated Generation of Diverse Tasks","created":"2021-06-26","cited_by_count":5,"area":null},{"id":"2210.03729","title":"Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning","created":"2022-10-07","cited_by_count":5,"area":null},{"id":"2305.01868","title":"Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2407.15086","title":"MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discovery","created":"2024-07-21","cited_by_count":5,"area":null},{"id":"2507.14850","title":"Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems","created":"2025-07-20","cited_by_count":5,"area":null},{"id":"2102.09854","title":"Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy","created":"2021-02-19","cited_by_count":4,"area":null},{"id":"2203.12686","title":"Possibility Before Utility: Learning And Using Hierarchical Affordances","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2205.15752","title":"Hierarchies of Reward Machines","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2302.02984","title":"Robust Subtask Learning for Compositional Generalization","created":"2023-02-06","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":"2311.00694","title":"Unleashing the Creative Mind: Language Model As Hierarchical Policy For Improved Exploration on Challenging Problem Solving","created":"2023-11-01","cited_by_count":4,"area":null},{"id":"2401.03546","title":"NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds","created":"2024-01-07","cited_by_count":4,"area":null},{"id":"2510.25345","title":"Informative Sample Selection Model for Skeleton-based Action Recognition with Limited Training Samples","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2110.00650","title":"Multi-lane Cruising Using Hierarchical Planning and Reinforcement Learning","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2112.07342","title":"Learning to Guide and to Be Guided in the Architect-Builder Problem","created":"2021-12-14","cited_by_count":3,"area":null},{"id":"2202.10222","title":"Robots Learn Increasingly Complex Tasks with Intrinsic Motivation and Automatic Curriculum Learning","created":"2022-02-11","cited_by_count":3,"area":null},{"id":"2204.10374","title":"Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learning","created":"2022-04-21","cited_by_count":3,"area":null},{"id":"2306.13872","title":"Learning from Pixels with Expert Observations","created":"2023-06-24","cited_by_count":3,"area":null},{"id":"2309.04459","title":"Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning","created":"2023-09-08","cited_by_count":3,"area":null},{"id":"2309.06420","title":"Verifiable Reinforcement Learning Systems via Compositionality","created":"2023-09-09","cited_by_count":3,"area":null},{"id":"2511.01107","title":"SLAP: Shortcut Learning for Abstract Planning","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2106.01434","title":"Robot in a China Shop: Using Reinforcement Learning for Location-Specific Navigation Behaviour","created":"2021-06-02","cited_by_count":2,"area":null},{"id":"2201.09653","title":"The Paradox of Choice: Using Attention in Hierarchical Reinforcement Learning","created":"2022-01-24","cited_by_count":2,"area":null},{"id":"2203.00669","title":"Hierarchical Reinforcement Learning with AI Planning Models","created":"2022-03-01","cited_by_count":2,"area":null},{"id":"2203.05985","title":"Graph Neural Networks for Relational Inductive Bias in Vision-based Deep Reinforcement Learning of Robot Control","created":"2022-03-11","cited_by_count":2,"area":null},{"id":"2204.02390","title":"Learning Pneumatic Non-Prehensile Manipulation with a Mobile Blower","created":"2022-04-05","cited_by_count":2,"area":null}],"next_cursor":"100"}