{"total":108,"rows":[{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458,"area":"wm"},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328,"area":"wm"},{"id":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215,"area":"offlinerl"},{"id":"2206.14244","title":"Masked World Models for Visual Control","created":"2022-06-28","cited_by_count":170,"area":"wm"},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2405.15223","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","created":"2024-05-24","cited_by_count":146,"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":"2602.06949","title":"DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos","created":"2026-02-06","cited_by_count":135,"area":"wm"},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116,"area":null},{"id":"2503.18938","title":"AdaWorld: Learning Adaptable World Models with Latent Actions","created":"2025-03-24","cited_by_count":114,"area":"wm"},{"id":"2403.08321","title":"ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation","created":"2024-03-13","cited_by_count":108,"area":null},{"id":"2304.00464","title":"UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning","created":"2023-04-02","cited_by_count":107,"area":null},{"id":"2302.00935","title":"Policy Expansion for Bridging Offline-to-Online Reinforcement Learning","created":"2023-02-02","cited_by_count":104,"area":"offlinerl"},{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"id":"2302.02408","title":"Multi-View Masked World Models for Visual Robotic Manipulation","created":"2023-02-05","cited_by_count":80,"area":"wm"},{"id":"2304.04782","title":"Reinforcement Learning from Passive Data via Latent Intentions","created":"2023-04-10","cited_by_count":68,"area":null},{"id":"2212.08860","title":"Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning","created":"2022-12-17","cited_by_count":60,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2211.12740","title":"Masked Autoencoding for Scalable and Generalizable Decision Making","created":"2022-11-23","cited_by_count":45,"area":"offlinerl"},{"id":"2305.18499","title":"Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning","created":"2023-05-29","cited_by_count":45,"area":"wm"},{"id":"2301.09816","title":"SMART: Self-supervised Multi-task pretrAining with contRol Transformers","created":"2023-01-24","cited_by_count":44,"area":null},{"id":"2409.12192","title":"DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control","created":"2024-09-18","cited_by_count":44,"area":"offlinerl"},{"id":"2206.01634","title":"Reinforcement Learning with Neural Radiance Fields","created":"2022-06-03","cited_by_count":43,"area":null},{"id":"2303.16958","title":"PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations","created":"2023-03-29","cited_by_count":42,"area":null},{"id":"2306.10711","title":"PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning","created":"2023-06-19","cited_by_count":42,"area":null},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"id":"2410.12822","title":"AVID: Adapting Video Diffusion Models to World Models","created":"2024-10-01","cited_by_count":37,"area":"wm"},{"id":"2309.13041","title":"Robotic Offline RL from Internet Videos via Value-Function Pre-Training","created":"2023-09-22","cited_by_count":33,"area":"offlinerl"},{"id":"2402.06665","title":"The Essential Role of Causality in Foundation World Models for Embodied AI","created":"2024-02-06","cited_by_count":32,"area":"wm"},{"id":"2305.16985","title":"Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation","created":"2023-05-26","cited_by_count":31,"area":null},{"id":"2602.02454","title":"World-Gymnast: Training Robots with Reinforcement Learning in a World Model","created":"2026-02-02","cited_by_count":27,"area":"wm"},{"id":"2402.14407","title":"Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training","created":"2024-02-22","cited_by_count":26,"area":"wm"},{"id":"2411.07223","title":"Grounding Video Models to Actions through Goal Conditioned Exploration","created":"2024-11-11","cited_by_count":26,"area":null},{"id":"2511.07732","title":"ViPRA: Video Prediction for Robot Actions","created":"2025-11-11","cited_by_count":26,"area":null},{"id":"2410.10738","title":"DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model","created":"2024-10-14","cited_by_count":25,"area":"wm"},{"id":"2512.24766","title":"Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow","created":"2025-12-31","cited_by_count":25,"area":null},{"id":"2402.02868","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","created":"2024-02-05","cited_by_count":23,"area":"deeprl"},{"id":"2209.07143","title":"HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generator","created":"2022-09-15","cited_by_count":22,"area":null},{"id":"2305.19476","title":"Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration","created":"2023-05-31","cited_by_count":22,"area":null},{"id":"2310.00344","title":"HarmonyDream: Task Harmonization Inside World Models","created":"2023-09-30","cited_by_count":22,"area":"wm"},{"id":"2402.18137","title":"DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning","created":"2024-02-28","cited_by_count":20,"area":null},{"id":"2606.20104","title":"Sensorimotor World Models: Perception for Action via Inverse Dynamics","created":"2026-06-18","cited_by_count":20,"area":"wm"},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2307.07909","title":"Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Training","created":"2023-07-16","cited_by_count":18,"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":"2305.06289","title":"Learning Video-Conditioned Policies for Unseen Manipulation Tasks","created":"2023-05-10","cited_by_count":16,"area":null},{"id":"2208.12345","title":"Light-weight probing of unsupervised representations for Reinforcement Learning","created":"2022-08-25","cited_by_count":15,"area":null},{"id":"2210.10763","title":"On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning","created":"2022-10-19","cited_by_count":15,"area":null},{"id":"2602.21736","title":"Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild","created":"2026-02-25","cited_by_count":15,"area":"vla"},{"id":"2410.03618","title":"Open-World Reinforcement Learning over Long Short-Term Imagination","created":"2024-10-04","cited_by_count":13,"area":"wm"},{"id":"2410.05429","title":"Diffusion Imitation from Observation","created":"2024-10-07","cited_by_count":13,"area":"diffusion"},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","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":"2506.19842","title":"ManiGaussian++: General Robotic Bimanual Manipulation with Hierarchical Gaussian World Model","created":"2025-06-24","cited_by_count":11,"area":"wm"},{"id":"2212.07398","title":"Policy Adaptation from Foundation Model Feedback","created":"2022-12-14","cited_by_count":10,"area":"mllm"},{"id":"2306.10695","title":"SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models","created":"2023-06-19","cited_by_count":10,"area":"offlinerl"},{"id":"2309.10790","title":"Guide Your Agent with Adaptive Multimodal Rewards","created":"2023-09-19","cited_by_count":10,"area":"offlinerl"},{"id":"2310.03023","title":"Human-oriented Representation Learning for Robotic Manipulation","created":"2023-10-04","cited_by_count":10,"area":null},{"id":"2404.17302","title":"Part-Guided 3D RL for Sim2Real Articulated Object Manipulation","created":"2024-04-26","cited_by_count":9,"area":null},{"id":"2210.00498","title":"EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model","created":"2022-10-02","cited_by_count":8,"area":null},{"id":"2306.05637","title":"On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2310.20178","title":"Learning to Discover Skills through Guidance","created":"2023-10-31","cited_by_count":8,"area":null},{"id":"2410.19989","title":"On-Robot Reinforcement Learning with Goal-Contrastive Rewards","created":"2024-10-25","cited_by_count":8,"area":"deeprl"},{"id":"2411.03169","title":"Pre-trained Visual Dynamics Representations for Efficient Policy Learning","created":"2024-11-05","cited_by_count":8,"area":"deeprl"},{"id":"2305.15260","title":"Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning","created":"2023-05-24","cited_by_count":7,"area":"wm"},{"id":"2405.02288","title":"Prospective Role of Foundation Models in Advancing Autonomous Vehicles","created":"2023-12-08","cited_by_count":7,"area":null},{"id":"2411.10175","title":"The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning","created":"2024-11-15","cited_by_count":7,"area":"deeprl"},{"id":"2503.08751","title":"Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning","created":"2025-03-11","cited_by_count":6,"area":"wm"},{"id":"2505.13144","title":"Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning","created":"2025-05-19","cited_by_count":6,"area":"offlinerl"},{"id":"2211.13337","title":"Multi-Environment Pretraining Enables Transfer to Action Limited Datasets","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2303.01668","title":"RePreM: Representation Pre-training with Masked Model for Reinforcement Learning","created":"2023-03-03","cited_by_count":5,"area":null},{"id":"2303.05092","title":"Task Aware Dreamer for Task Generalization in Reinforcement Learning","created":"2023-03-09","cited_by_count":5,"area":"wm"},{"id":"2312.02019","title":"Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models","created":"2023-12-04","cited_by_count":5,"area":"wm"},{"id":"2406.07253","title":"Hybrid Reinforcement Learning from Offline Observation Alone","created":"2024-06-11","cited_by_count":5,"area":"deeprl"},{"id":"2503.21383","title":"Controlling Large Language Model with Latent Actions","created":"2025-03-27","cited_by_count":5,"area":null},{"id":"2512.21586","title":"Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations","created":"2025-12-25","cited_by_count":5,"area":null},{"id":"2406.06037","title":"Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning","created":"2024-06-10","cited_by_count":4,"area":"deeprl"},{"id":"2412.10778","title":"Sample-efficient Unsupervised Policy Cloning from Ensemble Self-supervised Labeled Videos","created":"2024-12-14","cited_by_count":4,"area":null},{"id":"2502.01366","title":"Trajectory World Models for Heterogeneous Environments","created":"2025-02-03","cited_by_count":4,"area":"wm"},{"id":"2503.09871","title":"LuciBot: Automated Robot Policy Learning from Generated Videos","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2509.15536","title":"SAMPO:Scale-wise Autoregression with Motion PrOmpt for generative world models","created":"2025-09-19","cited_by_count":4,"area":"wm"},{"id":"2205.11357","title":"POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning","created":"2022-05-23","cited_by_count":3,"area":null},{"id":"2405.17039","title":"BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation","created":"2024-05-27","cited_by_count":3,"area":"wm"},{"id":"2408.01384","title":"NOLO: Navigate Only Look Once","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2510.02287","title":"MultiModal Action Conditioned Video Generation","created":"2025-10-02","cited_by_count":3,"area":"wm"},{"id":"2512.00961","title":"Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning","created":"2025-11-30","cited_by_count":3,"area":"diffusion"},{"id":"2404.18896","title":"Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models","created":"2024-04-29","cited_by_count":2,"area":"wm"},{"id":"2410.07584","title":"Imitation Learning with Limited Actions via Diffusion Planners and Deep Koopman Controllers","created":"2024-10-10","cited_by_count":2,"area":"offlinerl"},{"id":"2412.04273","title":"Reinforcement Learning from Wild Animal Videos","created":"2024-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2503.21018","title":"Offline Action-Free Learning of Ex-BMDPs by Comparing Diverse Datasets","created":"2025-03-26","cited_by_count":2,"area":null},{"id":"2501.11949","title":"GLAM: Global-Local Variation Awareness in Mamba-based World Model","created":"2025-01-21","cited_by_count":1,"area":"wm"},{"id":"2502.19544","title":"Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data","created":"2025-02-26","cited_by_count":1,"area":"wm"},{"id":"2505.05701","title":"Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning","created":"2025-05-09","cited_by_count":1,"area":"offlinerl"},{"id":"2505.06482","title":"Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach","created":"2025-05-10","cited_by_count":1,"area":"offlinerl"},{"id":"2601.07516","title":"Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions","created":"2026-01-12","cited_by_count":1,"area":"mllm"},{"id":"2605.12289","title":"PriorZero: Bridging Language Priors and World Models for Decision Making","created":"2026-05-12","cited_by_count":1,"area":"wm"},{"id":"2303.04452","title":"Grasping Student: semi-supervised learning for robotic manipulation","created":"2023-03-08","cited_by_count":0,"area":null},{"id":"2306.03360","title":"Model-Based Reinforcement Learning with Multi-Task Offline Pretraining","created":"2023-06-06","cited_by_count":0,"area":"wm"},{"id":"2308.10913","title":"Automated mapping of virtual environments with visual predictive coding","created":"2023-08-20","cited_by_count":0,"area":null},{"id":"2312.00592","title":"Tracking Object Positions in Reinforcement Learning: A Metric for Keypoint Detection (extended version)","created":"2023-12-01","cited_by_count":0,"area":null}],"next_cursor":"100"}