{"total":62,"rows":[{"id":"2302.12422","title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","created":"2023-02-24","cited_by_count":223,"area":"offlinerl"},{"id":"2309.10062","title":"SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models","created":"2023-09-18","cited_by_count":153,"area":"agents"},{"id":"2206.13499","title":"Prompting Decision Transformer for Few-Shot Policy Generalization","created":"2022-06-27","cited_by_count":146,"area":"offlinerl"},{"id":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99,"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":"2210.11435","title":"Learning and Retrieval from Prior Data for Skill-based Imitation Learning","created":"2022-10-20","cited_by_count":77,"area":"offlinerl"},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75,"area":"offlinerl"},{"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":"2207.07560","title":"Skill-based Model-based Reinforcement Learning","created":"2022-07-15","cited_by_count":50,"area":null},{"id":"1810.11043","title":"One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks","created":"2018-10-25","cited_by_count":33,"area":"offlinerl"},{"id":"2310.16014","title":"Human-in-the-Loop Task and Motion Planning for Imitation Learning","created":"2023-10-24","cited_by_count":29,"area":"offlinerl"},{"id":"2112.05062","title":"Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies","created":"2021-12-09","cited_by_count":26,"area":null},{"id":"2310.08581","title":"Universal Visual Decomposer: Long-Horizon Manipulation Made Easy","created":"2023-10-12","cited_by_count":25,"area":null},{"id":"2212.04590","title":"Learning Options via Compression","created":"2022-12-08","cited_by_count":22,"area":null},{"id":"2001.09227","title":"Active Task-Inference-Guided Deep Inverse Reinforcement Learning","created":"2020-01-24","cited_by_count":17,"area":"offlinerl"},{"id":"2103.10972","title":"Learning Task Decomposition with Ordered Memory Policy Network","created":"2021-03-19","cited_by_count":15,"area":null},{"id":"2203.13573","title":"Unsupervised Learning of Temporal Abstractions with Slot-based Transformers","created":"2022-03-25","cited_by_count":14,"area":null},{"id":"2410.17772","title":"Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models","created":"2024-10-23","cited_by_count":14,"area":null},{"id":"2411.03409","title":"STEER: Flexible Robotic Manipulation via Dense Language Grounding","created":"2024-11-05","cited_by_count":14,"area":null},{"id":"2210.07499","title":"Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks","created":"2022-10-14","cited_by_count":13,"area":null},{"id":"2406.17768","title":"EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data","created":"2024-06-25","cited_by_count":13,"area":"deeprl"},{"id":"2107.06317","title":"Inverse Contextual Bandits: Learning How Behavior Evolves over Time","created":"2021-07-13","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":"2010.03133","title":"Provable Hierarchical Imitation Learning via EM","created":"2020-10-07","cited_by_count":10,"area":"offlinerl"},{"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":"2209.01947","title":"MO2: Model-Based Offline Options","created":"2022-09-05","cited_by_count":10,"area":null},{"id":"1908.06769","title":"Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning","created":"2019-08-16","cited_by_count":8,"area":"offlinerl"},{"id":"2403.00929","title":"PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning","created":"2024-03-01","cited_by_count":8,"area":"offlinerl"},{"id":"2503.22122","title":"REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation","created":"2025-03-28","cited_by_count":8,"area":"mllm"},{"id":"1812.01483","title":"CompILE: Compositional Imitation Learning and Execution","created":"2018-12-04","cited_by_count":7,"area":"offlinerl"},{"id":"2203.03797","title":"Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrations","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2410.11584","title":"DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignment","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2502.15679","title":"BOSS: Benchmark for Observation Space Shift in Long-Horizon Task","created":"2025-02-21","cited_by_count":7,"area":"offlinerl"},{"id":"2503.10684","title":"Open-World Skill Discovery from Unsegmented Demonstrations","created":"2025-03-11","cited_by_count":7,"area":null},{"id":"2211.13743","title":"SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration","created":"2022-11-24","cited_by_count":6,"area":null},{"id":"2106.08112","title":"Contextualizing Meta-Learning via Learning to Decompose","created":"2021-06-15","cited_by_count":5,"area":null},{"id":"2202.04675","title":"Bayesian Nonparametrics for Offline Skill Discovery","created":"2022-02-09","cited_by_count":5,"area":"offlinerl"},{"id":"2203.12686","title":"Possibility Before Utility: Learning And Using Hierarchical Affordances","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2502.19899","title":"Shared Autonomy for Proximal Teaching","created":"2025-02-27","cited_by_count":4,"area":null},{"id":"2503.21406","title":"Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning","created":"2025-03-27","cited_by_count":4,"area":"offlinerl"},{"id":"2512.07371","title":"ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning","created":"2025-12-08","cited_by_count":4,"area":"offlinerl"},{"id":"2210.14685","title":"Leveraging Demonstrations with Latent Space Priors","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2306.06394","title":"PEAR: Primitive Enabled Adaptive Relabeling for Boosting Hierarchical Reinforcement Learning","created":"2023-06-10","cited_by_count":3,"area":null},{"id":"2309.14003","title":"Hierarchical Imitation Learning for Stochastic Environments","created":"2023-09-25","cited_by_count":3,"area":"offlinerl"},{"id":"2411.12173","title":"SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks","created":"2024-11-19","cited_by_count":3,"area":"deeprl"},{"id":"2102.13034","title":"AutoPreview: A Framework for Autopilot Behavior Understanding","created":"2021-02-25","cited_by_count":2,"area":null},{"id":"2304.03535","title":"CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learning","created":"2023-04-07","cited_by_count":2,"area":null},{"id":"2406.06577","title":"RAG-based Crowdsourcing Task Decomposition via Masked Contrastive Learning with Prompts","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"1811.07489","title":"Generalizing Robot Imitation Learning with Invariant Hidden Semi-Markov Models","created":"2018-11-19","cited_by_count":1,"area":"offlinerl"},{"id":"2205.07716","title":"Generalizing to New Tasks via One-Shot Compositional Subgoals","created":"2022-05-16","cited_by_count":1,"area":"offlinerl"},{"id":"2207.09243","title":"Abstract Demonstrations and Adaptive Exploration for Efficient and Stable Multi-step Sparse Reward Reinforcement Learning","created":"2022-07-19","cited_by_count":1,"area":null},{"id":"2310.11614","title":"Learning a Hierarchical Planner from Humans in Multiple Generations","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2111.09908","title":"Visual Goal-Directed Meta-Learning with Contextual Planning Networks","created":"2021-11-18","cited_by_count":0,"area":null},{"id":"2503.01871","title":"Data Augmentation for Instruction Following Policies via Trajectory Segmentation","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2507.16473","title":"Learning Temporal Abstractions via Variational Homomorphisms in Option-Induced Abstract MDPs","created":"2025-07-22","cited_by_count":0,"area":"lr"},{"id":"2510.10379","title":"RobotFleet: An Open-Source Framework for Centralized Multi-Robot Task Planning","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2511.03565","title":"Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances","created":"2025-11-05","cited_by_count":0,"area":"offlinerl"},{"id":"2602.17930","title":"MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance","created":"2026-02-20","cited_by_count":0,"area":"agents"},{"id":"2607.25731","title":"Tri-Manual Visuomotor Imitation Learning of Robot Policies","created":"2026-07-28","cited_by_count":0,"area":"offlinerl"},{"id":"2608.03753","title":"GORDON: Graph-based Object-centric Rewards for Decomposition of Long-Horizon Manipulation","created":"2026-08-04","cited_by_count":0,"area":"deeprl"},{"id":"2609.32993","title":"X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization","created":"2026-09-26","cited_by_count":0,"area":"agents"}],"next_cursor":null}