{"total":448,"rows":[{"id":"2302.01560","title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","created":"2023-02-03","cited_by_count":398,"area":"agents"},{"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":"2308.10901","title":"Structured World Models from Human Videos","created":"2023-08-21","cited_by_count":147,"area":"wm"},{"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":"2403.10506","title":"HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation","created":"2024-03-15","cited_by_count":112,"area":null},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"area":"offlinerl"},{"id":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99,"area":null},{"id":"2401.03360","title":"Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models","created":"2023-10-13","cited_by_count":91,"area":"diffusion"},{"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":"2310.10021","title":"Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance","created":"2023-10-16","cited_by_count":86,"area":"synth"},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2209.08959","title":"Latent Plans for Task-Agnostic Offline Reinforcement Learning","created":"2022-09-19","cited_by_count":81,"area":"offlinerl"},{"id":"2407.13032","title":"Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems","created":"2024-07-17","cited_by_count":81,"area":"agents"},{"id":"2208.12403","title":"BITS: Bi-level Imitation for Traffic Simulation","created":"2022-08-26","cited_by_count":80,"area":null},{"id":"2110.03655","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","created":"2021-10-07","cited_by_count":78,"area":null},{"id":"2112.11561","title":"Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions","created":"2021-12-21","cited_by_count":73,"area":"driving"},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"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":"2110.15360","title":"Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives","created":"2021-10-28","cited_by_count":65,"area":null},{"id":"2307.08927","title":"Multi-Stage Cable Routing through Hierarchical Imitation Learning","created":"2023-07-18","cited_by_count":60,"area":"offlinerl"},{"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":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57,"area":null},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2110.05740","title":"Temporal Abstraction in Reinforcement Learning with the Successor Representation","created":"2021-10-12","cited_by_count":54,"area":null},{"id":"2406.00681","title":"Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient","created":"2024-06-02","cited_by_count":51,"area":"diffusion"},{"id":"2312.04549","title":"PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play","created":"2023-12-07","cited_by_count":50,"area":"diffusion"},{"id":"2309.00987","title":"Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation","created":"2023-09-02","cited_by_count":49,"area":null},{"id":"2310.02172","title":"Lyfe Agents: Generative agents for low-cost real-time social interactions","created":"2023-10-03","cited_by_count":49,"area":"agents"},{"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":"2106.02940","title":"Same State, Different Task: Continual Reinforcement Learning without Interference","created":"2021-06-05","cited_by_count":43,"area":null},{"id":"2604.03208","title":"Hierarchical Planning with Latent World Models","created":"2026-04-03","cited_by_count":43,"area":"wm"},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","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":"2402.04764","title":"Code as Reward: Empowering Reinforcement Learning with VLMs","created":"2024-02-07","cited_by_count":39,"area":"mllm"},{"id":"2110.10809","title":"Hierarchical Skills for Efficient Exploration","created":"2021-10-20","cited_by_count":38,"area":null},{"id":"2305.04412","title":"Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors","created":"2023-05-08","cited_by_count":36,"area":"driving"},{"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":"2103.15793","title":"LASER: Learning a Latent Action Space for Efficient Reinforcement Learning","created":"2021-03-29","cited_by_count":32,"area":null},{"id":"2412.19726","title":"Position: Theory of Mind Benchmarks are Broken for Large Language Models","created":"2024-12-27","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":"2202.13675","title":"A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning","created":"2022-02-28","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":"2209.08890","title":"An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey","created":"2022-09-19","cited_by_count":28,"area":null},{"id":"2102.06741","title":"Discovery of Options via Meta-Learned Subgoals","created":"2021-02-12","cited_by_count":27,"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":"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":"2112.05062","title":"Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies","created":"2021-12-09","cited_by_count":26,"area":null},{"id":"2210.07940","title":"AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments","created":"2022-10-14","cited_by_count":26,"area":"wm"},{"id":"2405.20692","title":"In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought","created":"2024-05-31","cited_by_count":26,"area":"lr"},{"id":"2505.10819","title":"PoE-World: Compositional World Modeling with Products of Programmatic Experts","created":"2025-05-16","cited_by_count":26,"area":"wm"},{"id":"2106.05262","title":"TempoRL: Learning When to Act","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2112.03097","title":"Flexible Option Learning","created":"2021-12-06","cited_by_count":25,"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":"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":"2112.04216","title":"Specializing Versatile Skill Libraries using Local Mixture of Experts","created":"2021-12-08","cited_by_count":24,"area":"moe"},{"id":"2211.02231","title":"Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics","created":"2022-11-04","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":"2203.05960","title":"Policy Architectures for Compositional Generalization in Control","created":"2022-03-10","cited_by_count":23,"area":null},{"id":"2401.05821","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","created":"2024-01-11","cited_by_count":23,"area":"deeprl"},{"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":"2402.15809","title":"Empowering Large Language Model Agents through Action Learning","created":"2024-02-24","cited_by_count":22,"area":"agents"},{"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":"2504.03515","title":"Dexterous Manipulation through Imitation Learning: A Survey","created":"2025-04-04","cited_by_count":21,"area":"offlinerl"},{"id":"2103.06224","title":"An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning","created":"2021-03-10","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":"2307.10710","title":"Reparameterized Policy Learning for Multimodal Trajectory Optimization","created":"2023-07-20","cited_by_count":20,"area":null},{"id":"2509.03581","title":"Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents","created":"2025-09-03","cited_by_count":20,"area":"lr"},{"id":"2103.07084","title":"Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information","created":"2021-03-12","cited_by_count":19,"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":"2106.05530","title":"Adversarial Option-Aware Hierarchical Imitation Learning","created":"2021-06-10","cited_by_count":19,"area":"offlinerl"},{"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":"2209.10113","title":"Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning","created":"2022-09-20","cited_by_count":18,"area":null},{"id":"2210.12250","title":"STAP: Sequencing Task-Agnostic Policies","created":"2022-10-21","cited_by_count":18,"area":null},{"id":"2212.07407","title":"Cross-Domain Transfer via Semantic Skill Imitation","created":"2022-12-14","cited_by_count":18,"area":null},{"id":"2602.16165","title":"HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents","created":"2026-02-18","cited_by_count":18,"area":"agents"},{"id":"2202.03466","title":"Reward-Respecting Subtasks for Model-Based Reinforcement Learning","created":"2022-02-07","cited_by_count":16,"area":null},{"id":"2206.08737","title":"N$^2$M$^2$: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments","created":"2022-06-17","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":"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":"2109.11328","title":"Reinforcement Learning Under Algorithmic Triage","created":"2021-09-23","cited_by_count":15,"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":"2301.12962","title":"Hierarchical Imitation Learning with Vector Quantized Models","created":"2023-01-30","cited_by_count":15,"area":"offlinerl"},{"id":"2303.13512","title":"Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition","created":"2023-03-23","cited_by_count":15,"area":"alignment"},{"id":"2407.02666","title":"Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models","created":"2024-07-02","cited_by_count":15,"area":"lr"},{"id":"2410.20018","title":"GHIL-Glue: Hierarchical Control with Filtered Subgoal Images","created":"2024-10-26","cited_by_count":15,"area":"deeprl"},{"id":"2112.07066","title":"Continual Learning In Environments With Polynomial Mixing Times","created":"2021-12-13","cited_by_count":14,"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":"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":"2306.01242","title":"Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2311.00267","title":"Rethinking Decision Transformer via Hierarchical Reinforcement Learning","created":"2023-11-01","cited_by_count":14,"area":"offlinerl"},{"id":"2411.03409","title":"STEER: Flexible Robotic Manipulation via Dense Language Grounding","created":"2024-11-05","cited_by_count":14,"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}],"next_cursor":"100"}