{"total":337,"rows":[{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228,"area":"agents"},{"id":"2010.13611","title":"OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning","created":"2020-10-26","cited_by_count":166,"area":"offlinerl"},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2108.03332","title":"BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments","created":"2021-08-06","cited_by_count":165,"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":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134,"area":null},{"id":"2311.07226","title":"Large Language Models for Robotics: A Survey","created":"2023-11-13","cited_by_count":133,"area":null},{"id":"2312.03664","title":"Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia","created":"2023-12-06","cited_by_count":126,"area":"agents"},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"area":"offlinerl"},{"id":"2206.04114","title":"Deep Hierarchical Planning from Pixels","created":"2022-06-08","cited_by_count":101,"area":"wm"},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87,"area":null},{"id":"2109.13841","title":"Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation","created":"2021-09-28","cited_by_count":83,"area":"offlinerl"},{"id":"2208.12403","title":"BITS: Bi-level Imitation for Traffic Simulation","created":"2022-08-26","cited_by_count":80,"area":null},{"id":"2401.02644","title":"Simple Hierarchical Planning with Diffusion","created":"2024-01-05","cited_by_count":73,"area":"diffusion"},{"id":"2101.04882","title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","created":"2021-01-13","cited_by_count":72,"area":null},{"id":"2106.13105","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","created":"2021-06-24","cited_by_count":67,"area":null},{"id":"2311.02058","title":"LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery","created":"2023-11-03","cited_by_count":67,"area":"offlinerl"},{"id":"2310.03720","title":"SteP: Stacked LLM Policies for Web Actions","created":"2023-10-05","cited_by_count":66,"area":null},{"id":"2110.15360","title":"Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives","created":"2021-10-28","cited_by_count":65,"area":null},{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","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":"2101.06521","title":"Hierarchical Reinforcement Learning By Discovering Intrinsic Options","created":"2021-01-16","cited_by_count":58,"area":null},{"id":"2206.10680","title":"Learning Neuro-Symbolic Skills for Bilevel Planning","created":"2022-06-21","cited_by_count":58,"area":null},{"id":"2508.05606","title":"Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision","created":"2025-08-07","cited_by_count":56,"area":"lr"},{"id":"2202.08417","title":"Retrieval-Augmented Reinforcement Learning","created":"2022-02-17","cited_by_count":53,"area":"rag"},{"id":"2405.01792","title":"Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots","created":"2024-05-03","cited_by_count":48,"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":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40,"area":null},{"id":"2211.13746","title":"Melting Pot 2.0","created":"2022-11-24","cited_by_count":40,"area":null},{"id":"2110.14770","title":"TRAIL: Near-Optimal Imitation Learning with Suboptimal Data","created":"2021-10-27","cited_by_count":39,"area":"offlinerl"},{"id":"2110.10809","title":"Hierarchical Skills for Efficient Exploration","created":"2021-10-20","cited_by_count":38,"area":null},{"id":"2210.12631","title":"LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulation","created":"2022-10-23","cited_by_count":34,"area":null},{"id":"2111.08611","title":"Stochastic Extragradient: General Analysis and Improved Rates","created":"2021-11-16","cited_by_count":31,"area":null},{"id":"2105.08692","title":"Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition","created":"2021-05-18","cited_by_count":30,"area":null},{"id":"2309.04612","title":"Self-optimizing Feature Generation via Categorical Hashing Representation and Hierarchical Reinforcement Crossing","created":"2023-09-08","cited_by_count":30,"area":null},{"id":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","cited_by_count":29,"area":null},{"id":"2106.14305","title":"Unsupervised Skill Discovery with Bottleneck Option Learning","created":"2021-06-27","cited_by_count":28,"area":null},{"id":"2104.09122","title":"Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning","created":"2021-04-19","cited_by_count":27,"area":"moe"},{"id":"2207.07730","title":"How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2310.17966","title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","created":"2023-10-27","cited_by_count":26,"area":"offlinerl"},{"id":"2112.03097","title":"Flexible Option Learning","created":"2021-12-06","cited_by_count":25,"area":null},{"id":"2210.06964","title":"Causality-driven Hierarchical Structure Discovery for Reinforcement Learning","created":"2022-10-13","cited_by_count":24,"area":null},{"id":"2412.08542","title":"MaestroMotif: Skill Design from Artificial Intelligence Feedback","created":"2024-12-11","cited_by_count":24,"area":null},{"id":"2101.06197","title":"Deciding What to Learn: A Rate-Distortion Approach","created":"2021-01-15","cited_by_count":23,"area":null},{"id":"2505.12737","title":"Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning","created":"2025-05-19","cited_by_count":23,"area":"offlinerl"},{"id":"2212.04590","title":"Learning Options via Compression","created":"2022-12-08","cited_by_count":22,"area":null},{"id":"2306.16700","title":"Dynamic-Resolution Model Learning for Object Pile Manipulation","created":"2023-06-29","cited_by_count":22,"area":null},{"id":"2108.11204","title":"Subgoal Search For Complex Reasoning Tasks","created":"2021-08-25","cited_by_count":21,"area":null},{"id":"2112.03100","title":"Hierarchical Reinforcement Learning with Timed Subgoals","created":"2021-12-06","cited_by_count":21,"area":null},{"id":"2207.04136","title":"CompoSuite: A Compositional Reinforcement Learning Benchmark","created":"2022-07-08","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":"2204.06127","title":"Reinforcement learning on graphs: A survey","created":"2022-04-13","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":"2103.07607","title":"Solving Compositional Reinforcement Learning Problems via Task Reduction","created":"2021-03-13","cited_by_count":19,"area":null},{"id":"2110.07246","title":"HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism","created":"2021-10-14","cited_by_count":19,"area":null},{"id":"2210.05150","title":"DHRL: A Graph-Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning","created":"2022-10-11","cited_by_count":19,"area":null},{"id":"2602.11865","title":"Intelligent AI Delegation","created":"2026-02-12","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":"2107.05627","title":"Hierarchical Neural Dynamic Policies","created":"2021-07-12","cited_by_count":17,"area":null},{"id":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","cited_by_count":17,"area":"deeprl"},{"id":"2109.04150","title":"Self-supervised Reinforcement Learning with Independently Controllable Subgoals","created":"2021-09-09","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":"2103.10972","title":"Learning Task Decomposition with Ordered Memory Policy Network","created":"2021-03-19","cited_by_count":15,"area":null},{"id":"2104.06521","title":"TAAC: Temporally Abstract Actor-Critic for Continuous Control","created":"2021-04-13","cited_by_count":15,"area":null},{"id":"2410.20018","title":"GHIL-Glue: Hierarchical Control with Filtered Subgoal Images","created":"2024-10-26","cited_by_count":15,"area":"deeprl"},{"id":"2206.01095","title":"Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise","created":"2022-06-02","cited_by_count":14,"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":"2102.00824","title":"HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging","created":"2021-01-18","cited_by_count":13,"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":"2107.05842","title":"Motion Planning by Learning the Solution Manifold in Trajectory Optimization","created":"2021-07-13","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":"2411.07104","title":"Learning Multi-Agent Loco-Manipulation for Long-Horizon Quadrupedal Pushing","created":"2024-11-11","cited_by_count":13,"area":null},{"id":"2203.02214","title":"Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization","created":"2022-03-04","cited_by_count":12,"area":"offlinerl"},{"id":"2411.02478","title":"Imagining and building wise machines: The centrality of AI metacognition","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2506.07744","title":"Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning","created":"2025-06-09","cited_by_count":12,"area":"offlinerl"},{"id":"2104.06411","title":"Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning","created":"2021-04-13","cited_by_count":11,"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":"2109.11178","title":"Hierarchies of Planning and Reinforcement Learning for Robot Navigation","created":"2021-09-23","cited_by_count":11,"area":null},{"id":"2207.13649","title":"Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes","created":"2022-07-27","cited_by_count":11,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2406.00483","title":"Exploring the limits of Hierarchical World Models in Reinforcement Learning","created":"2024-06-01","cited_by_count":11,"area":"wm"},{"id":"2410.18065","title":"SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation","created":"2024-10-23","cited_by_count":11,"area":"offlinerl"},{"id":"2505.14975","title":"Flattening Hierarchies with Policy Bootstrapping","created":"2025-05-20","cited_by_count":11,"area":"synth"},{"id":"2010.03133","title":"Provable Hierarchical Imitation Learning via EM","created":"2020-10-07","cited_by_count":10,"area":"offlinerl"},{"id":"2111.00213","title":"Adjacency constraint for efficient hierarchical reinforcement learning","created":"2021-10-30","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":"2411.12155","title":"Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning","created":"2024-11-19","cited_by_count":10,"area":"deeprl"},{"id":"2510.07730","title":"DEAS: DEtached value learning with Action Sequence for Scalable Offline RL","created":"2025-10-09","cited_by_count":10,"area":"offlinerl"},{"id":"2102.11329","title":"Action Redundancy in Reinforcement Learning","created":"2021-02-22","cited_by_count":9,"area":null},{"id":"2104.11707","title":"DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies","created":"2021-04-23","cited_by_count":9,"area":null},{"id":"2405.17009","title":"Position: Foundation Agents as the Paradigm Shift for Decision Making","created":"2024-05-27","cited_by_count":9,"area":"agents"},{"id":"2408.15332","title":"What makes math problems hard for reinforcement learning: a case study","created":"2024-08-27","cited_by_count":9,"area":"deeprl"},{"id":"2410.18416","title":"SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions","created":"2024-10-24","cited_by_count":9,"area":null},{"id":"2105.00990","title":"Hierarchical Reinforcement Learning for Air Combat at DARPA's AlphaDogfight Trials","created":"2021-05-03","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}],"next_cursor":"100"}