{"total":384,"rows":[{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427,"area":"offlinerl"},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694,"area":null},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407,"area":null},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395,"area":"offlinerl"},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327,"area":null},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304,"area":"offlinerl"},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2409.00588","title":"Diffusion Policy Policy Optimization","created":"2024-09-01","cited_by_count":280,"area":"diffusion"},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279,"area":"lr"},{"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":"2301.10677","title":"Imitating Human Behaviour with Diffusion Models","created":"2023-01-25","cited_by_count":263,"area":"diffusion"},{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237,"area":"offlinerl"},{"id":"2304.02532","title":"Goal-Conditioned Imitation Learning using Score-based Diffusion Policies","created":"2023-04-05","cited_by_count":236,"area":"diffusion"},{"id":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231,"area":"offlinerl"},{"id":"2210.06407","title":"Interactive Language: Talking to Robots in Real Time","created":"2022-10-12","cited_by_count":218,"area":null},{"id":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":217,"area":"mllm"},{"id":"2005.07648","title":"Language Conditioned Imitation Learning over Unstructured Data","created":"2020-05-15","cited_by_count":209,"area":"offlinerl"},{"id":"2306.00958","title":"LIV: Language-Image Representations and Rewards for Robotic Control","created":"2023-06-01","cited_by_count":188,"area":null},{"id":"2112.10751","title":"RvS: What is Essential for Offline RL via Supervised Learning?","created":"2021-12-20","cited_by_count":185,"area":"offlinerl"},{"id":"2505.18719","title":"VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning","created":"2025-05-24","cited_by_count":176,"area":"vla"},{"id":"2405.07503","title":"Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation","created":"2024-05-13","cited_by_count":166,"area":"diffusion"},{"id":"2403.03181","title":"Behavior Generation with Latent Actions","created":"2024-03-05","cited_by_count":160,"area":"diffusion"},{"id":"2203.03580","title":"The Unsurprising Effectiveness of Pre-Trained Vision Models for Control","created":"2022-03-07","cited_by_count":155,"area":null},{"id":"2502.05450","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy","created":"2025-02-08","cited_by_count":154,"area":"vla"},{"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":"2310.07899","title":"RoboCLIP: One Demonstration is Enough to Learn Robot Policies","created":"2023-10-11","cited_by_count":134,"area":"offlinerl"},{"id":"2510.12276","title":"Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model","created":"2025-10-14","cited_by_count":134,"area":"vla"},{"id":"2305.12821","title":"FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation","created":"2023-05-22","cited_by_count":133,"area":"offlinerl"},{"id":"2110.09514","title":"Discovering and Achieving Goals via World Models","created":"2021-10-18","cited_by_count":131,"area":"wm"},{"id":"2501.16664","title":"Improving Vision-Language-Action Model with Online Reinforcement Learning","created":"2025-01-28","cited_by_count":116,"area":"mllm"},{"id":"2305.16317","title":"Parallel Sampling of Diffusion Models","created":"2023-05-25","cited_by_count":112,"area":"diffusion"},{"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":"2210.10047","title":"From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data","created":"2022-10-18","cited_by_count":103,"area":null},{"id":"2505.22094","title":"ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning","created":"2025-05-28","cited_by_count":97,"area":"diffusion"},{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"id":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93,"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":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"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":"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":"2209.08959","title":"Latent Plans for Task-Agnostic Offline Reinforcement Learning","created":"2022-09-19","cited_by_count":81,"area":"offlinerl"},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80,"area":null},{"id":"2402.03610","title":"RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents","created":"2024-02-06","cited_by_count":80,"area":"mllm"},{"id":"2106.03400","title":"Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning","created":"2021-06-07","cited_by_count":79,"area":"offlinerl"},{"id":"2412.06685","title":"Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone","created":"2024-12-09","cited_by_count":79,"area":"offlinerl"},{"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":"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":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76,"area":null},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75,"area":"offlinerl"},{"id":"2410.05273","title":"HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers","created":"2024-09-12","cited_by_count":75,"area":"mllm"},{"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":"2212.05711","title":"CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning","created":"2022-12-12","cited_by_count":71,"area":"offlinerl"},{"id":"2204.11134","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","created":"2022-04-23","cited_by_count":70,"area":null},{"id":"2507.01016","title":"VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers","created":"2025-07-01","cited_by_count":70,"area":"vla"},{"id":"2508.13073","title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","created":"2025-08-18","cited_by_count":69,"area":"vla"},{"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":"2407.01812","title":"Equivariant Diffusion Policy","created":"2024-07-01","cited_by_count":66,"area":"diffusion"},{"id":"2110.15360","title":"Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives","created":"2021-10-28","cited_by_count":65,"area":null},{"id":"2205.13554","title":"Training and Inference on Any-Order Autoregressive Models the Right Way","created":"2022-05-26","cited_by_count":64,"area":null},{"id":"2102.00714","title":"NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning","created":"2021-02-01","cited_by_count":63,"area":"offlinerl"},{"id":"2412.07762","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","created":"2024-12-10","cited_by_count":63,"area":"offlinerl"},{"id":"2307.08927","title":"Multi-Stage Cable Routing through Hierarchical Imitation Learning","created":"2023-07-18","cited_by_count":60,"area":"offlinerl"},{"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":"2505.23458","title":"Diffusion Guidance Is a Controllable Policy Improvement Operator","created":"2025-05-29","cited_by_count":58,"area":"offlinerl"},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2202.04628","title":"Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration","created":"2022-02-09","cited_by_count":54,"area":null},{"id":"2409.01083","title":"Affordance-based Robot Manipulation with Flow Matching","created":"2024-09-02","cited_by_count":54,"area":"diffusion"},{"id":"2409.16578","title":"FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning","created":"2024-09-25","cited_by_count":54,"area":"deeprl"},{"id":"2402.14606","title":"Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations","created":"2024-02-22","cited_by_count":53,"area":"offlinerl"},{"id":"2405.01534","title":"Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks","created":"2024-05-02","cited_by_count":52,"area":null},{"id":"2408.17355","title":"Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling","created":"2024-08-30","cited_by_count":52,"area":null},{"id":"2205.11790","title":"Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning","created":"2022-05-24","cited_by_count":50,"area":"offlinerl"},{"id":"2207.07560","title":"Skill-based Model-based Reinforcement Learning","created":"2022-07-15","cited_by_count":50,"area":null},{"id":"2312.04549","title":"PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play","created":"2023-12-07","cited_by_count":50,"area":"diffusion"},{"id":"2605.12090","title":"World Action Models: The Next Frontier in Embodied AI","created":"2026-05-12","cited_by_count":50,"area":"wm"},{"id":"2302.05103","title":"Controllability-Aware Unsupervised Skill Discovery","created":"2023-02-10","cited_by_count":49,"area":null},{"id":"2509.19012","title":"Pure Vision Language Action (VLA) Models: A Comprehensive Survey","created":"2025-09-23","cited_by_count":49,"area":"mllm"},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2411.09153","title":"VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation","created":"2024-11-14","cited_by_count":46,"area":"diffusion"},{"id":"2503.07135","title":"VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation","created":"2025-03-10","cited_by_count":46,"area":null},{"id":"2503.14858","title":"1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities","created":"2025-03-19","cited_by_count":45,"area":"deeprl"},{"id":"2402.13181","title":"DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models","created":"2024-02-20","cited_by_count":44,"area":"offlinerl"},{"id":"2409.12192","title":"DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control","created":"2024-09-18","cited_by_count":44,"area":"offlinerl"},{"id":"2202.02433","title":"Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching","created":"2022-02-04","cited_by_count":43,"area":"offlinerl"},{"id":"2310.09289","title":"An Unbiased Look at Datasets for Visuo-Motor Pre-Training","created":"2023-10-13","cited_by_count":42,"area":null},{"id":"2401.15443","title":"DiffuserLite: Towards Real-time Diffusion Planning","created":"2024-01-27","cited_by_count":42,"area":null},{"id":"2504.08438","title":"Diffusion Models for Robotic Manipulation: A Survey","created":"2025-04-11","cited_by_count":41,"area":"diffusion"},{"id":"2312.12444","title":"What Makes Pre-Trained Visual Representations Successful for Robust Manipulation?","created":"2023-11-03","cited_by_count":39,"area":null},{"id":"2406.09509","title":"CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making","created":"2024-06-13","cited_by_count":39,"area":"diffusion"},{"id":"2110.10067","title":"CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents","created":"2021-10-19","cited_by_count":38,"area":null},{"id":"2107.08981","title":"Hierarchical Few-Shot Imitation with Skill Transition Models","created":"2021-07-19","cited_by_count":37,"area":null},{"id":"2204.11828","title":"Skill-based Meta-Reinforcement Learning","created":"2022-04-25","cited_by_count":37,"area":null},{"id":"2406.00439","title":"Learning Manipulation by Predicting Interaction","created":"2024-06-01","cited_by_count":37,"area":null},{"id":"2301.12842","title":"Direct Preference-based Policy Optimization without Reward Modeling","created":"2023-01-30","cited_by_count":36,"area":"alignment"},{"id":"2310.20141","title":"Contrastive Difference Predictive Coding","created":"2023-10-31","cited_by_count":36,"area":null},{"id":"2502.10550","title":"Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning","created":"2025-02-14","cited_by_count":36,"area":"deeprl"},{"id":"2210.13846","title":"Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning","created":"2022-10-25","cited_by_count":34,"area":"offlinerl"},{"id":"2112.09605","title":"Autonomous Reinforcement Learning: Formalism and Benchmarking","created":"2021-12-17","cited_by_count":33,"area":null}],"next_cursor":"100"}