{"total":101,"rows":[{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747,"area":"wm"},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478,"area":"wm"},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345,"area":"offlinerl"},{"id":"2410.11758","title":"Latent Action Pretraining from Videos","created":"2024-10-15","cited_by_count":321,"area":"vla"},{"id":"2512.13030","title":"Motus: A Unified Latent Action World Model","created":"2025-12-15","cited_by_count":251,"area":"wm"},{"id":"2309.02473","title":"A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges","created":"2023-09-05","cited_by_count":148,"area":"offlinerl"},{"id":"2006.04678","title":"Primal Wasserstein Imitation Learning","created":"2020-06-08","cited_by_count":121,"area":"offlinerl"},{"id":"2312.10812","title":"Learning to Act without Actions","created":"2023-12-17","cited_by_count":121,"area":"wm"},{"id":"2602.10098","title":"VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model","created":"2026-02-10","cited_by_count":118,"area":"wm"},{"id":"2503.18938","title":"AdaWorld: Learning Adaptable World Models with Latent Actions","created":"2025-03-24","cited_by_count":114,"area":"wm"},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108,"area":null},{"id":"2106.03911","title":"XIRL: Cross-embodiment Inverse Reinforcement Learning","created":"2021-06-07","cited_by_count":107,"area":"offlinerl"},{"id":"1905.13566","title":"Recent Advances in Imitation Learning from Observation","created":"2019-05-30","cited_by_count":93,"area":"offlinerl"},{"id":"2004.04650","title":"State-Only Imitation Learning for Dexterous Manipulation","created":"2020-04-07","cited_by_count":91,"area":"offlinerl"},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87,"area":null},{"id":"1905.10948","title":"Provably Efficient Imitation Learning from Observation Alone","created":"2019-05-27","cited_by_count":78,"area":"offlinerl"},{"id":"1911.10947","title":"State Alignment-based Imitation Learning","created":"2019-11-21","cited_by_count":73,"area":"offlinerl"},{"id":"2102.13185","title":"Off-Policy Imitation Learning from Observations","created":"2021-02-25","cited_by_count":70,"area":"offlinerl"},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58,"area":"offlinerl"},{"id":"2601.05230","title":"Learning Latent Action World Models In The Wild","created":"2026-01-08","cited_by_count":47,"area":"wm"},{"id":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","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":"2502.00379","title":"Latent Action Learning Requires Supervision in the Presence of Distractors","created":"2025-02-01","cited_by_count":44,"area":null},{"id":"2002.10544","title":"Provable Representation Learning for Imitation Learning via Bi-level Optimization","created":"2020-02-24","cited_by_count":41,"area":"offlinerl"},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"area":null},{"id":"2506.15691","title":"What Do Latent Action Models Actually Learn?","created":"2025-05-27","cited_by_count":32,"area":null},{"id":"2204.02392","title":"Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models","created":"2022-04-05","cited_by_count":27,"area":null},{"id":"2601.02427","title":"NitroGen: An Open Foundation Model for Generalist Gaming Agents","created":"2026-01-04","cited_by_count":27,"area":"agents"},{"id":"2504.16925","title":"Latent Diffusion Planning for Imitation Learning","created":"2025-04-23","cited_by_count":26,"area":"diffusion"},{"id":"1905.09335","title":"Imitation Learning from Video by Leveraging Proprioception","created":"2019-05-22","cited_by_count":23,"area":"offlinerl"},{"id":"2108.01069","title":"Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning","created":"2021-08-02","cited_by_count":23,"area":"offlinerl"},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21,"area":null},{"id":"2204.08058","title":"MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration","created":"2022-04-17","cited_by_count":20,"area":null},{"id":"2202.03481","title":"A Ranking Game for Imitation Learning","created":"2022-02-07","cited_by_count":18,"area":"offlinerl"},{"id":"2207.00244","title":"Discriminator-Guided Model-Based Offline Imitation Learning","created":"2022-07-01","cited_by_count":17,"area":"offlinerl"},{"id":"2405.19883","title":"From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems","created":"2024-05-30","cited_by_count":17,"area":null},{"id":"2211.00539","title":"Dungeons and Data: A Large-Scale NetHack Dataset","created":"2022-11-01","cited_by_count":16,"area":"offlinerl"},{"id":"2404.19456","title":"A Survey of Imitation Learning Methods, Environments and Metrics","created":"2024-04-30","cited_by_count":16,"area":"offlinerl"},{"id":"2603.04553","title":"Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling","created":"2026-03-04","cited_by_count":15,"area":"wm"},{"id":"2306.12860","title":"Learning from Visual Observation via Offline Pretrained State-to-Go Transformer","created":"2023-06-22","cited_by_count":14,"area":null},{"id":"2502.07600","title":"PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning","created":"2025-02-11","cited_by_count":14,"area":null},{"id":"2107.03851","title":"Imitation by Predicting Observations","created":"2021-07-08","cited_by_count":13,"area":"offlinerl"},{"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":"2204.11446","title":"Imitation Learning from Observations under Transition Model Disparity","created":"2022-04-25","cited_by_count":11,"area":"offlinerl"},{"id":"2312.00548","title":"Domain Adaptive Imitation Learning with Visual Observation","created":"2023-12-01","cited_by_count":11,"area":"offlinerl"},{"id":"2512.09929","title":"Closing the Train-Test Gap in World Models for Gradient-Based Planning","created":"2025-12-10","cited_by_count":11,"area":"wm"},{"id":"2202.00243","title":"Adversarial Imitation Learning from Video using a State Observer","created":"2022-02-01","cited_by_count":10,"area":"offlinerl"},{"id":"2310.07433","title":"Imitation Learning from Observation with Automatic Discount Scheduling","created":"2023-10-11","cited_by_count":10,"area":"offlinerl"},{"id":"2403.09976","title":"AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors","created":"2024-03-15","cited_by_count":10,"area":"wm"},{"id":"2406.08805","title":"A Dual Approach to Imitation Learning from Observations with Offline Datasets","created":"2024-06-13","cited_by_count":10,"area":"offlinerl"},{"id":"2602.10104","title":"Olaf-World: Orienting Latent Actions for Video World Modeling","created":"2026-02-10","cited_by_count":10,"area":"wm"},{"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":"2202.06003","title":"Robust Learning from Observation with Model Misspecification","created":"2022-02-12","cited_by_count":9,"area":"offlinerl"},{"id":"2203.00715","title":"Learning Robust Real-Time Cultural Transmission without Human Data","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2210.00066","title":"Improving Policy Learning via Language Dynamics Distillation","created":"2022-09-30","cited_by_count":9,"area":null},{"id":"2502.09680","title":"Object-Centric Latent Action Learning","created":"2025-02-13","cited_by_count":9,"area":null},{"id":"2204.12458","title":"Learning Value Functions from Undirected State-only Experience","created":"2022-04-26","cited_by_count":8,"area":"offlinerl"},{"id":"2411.03169","title":"Pre-trained Visual Dynamics Representations for Efficient Policy Learning","created":"2024-11-05","cited_by_count":8,"area":"deeprl"},{"id":"2602.16229","title":"Factored Latent Action World Models","created":"2026-02-18","cited_by_count":7,"area":"wm"},{"id":"2210.09566","title":"Simple Emergent Action Representations from Multi-Task Policy Training","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2509.26627","title":"TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance","created":"2025-09-30","cited_by_count":6,"area":"deeprl"},{"id":"2602.02259","title":"Segment to Focus: Guiding Latent Action Models in the Presence of Distractors","created":"2026-02-02","cited_by_count":6,"area":null},{"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":"2502.19859","title":"IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic","created":"2025-02-27","cited_by_count":5,"area":"offlinerl"},{"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":"2602.20231","title":"UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models","created":"2026-02-23","cited_by_count":5,"area":"vla"},{"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":"2608.19613","title":"What Matters for Latent Actions in Robot Learning","created":"2026-08-20","cited_by_count":4,"area":null},{"id":"2106.13280","title":"Hierarchically Integrated Models: Learning to Navigate from Heterogeneous Robots","created":"2021-06-24","cited_by_count":3,"area":null},{"id":"2206.11299","title":"Latent Policies for Adversarial Imitation Learning","created":"2022-06-22","cited_by_count":3,"area":"offlinerl"},{"id":"2407.04856","title":"Explorative Imitation Learning: A Path Signature Approach for Continuous Environments","created":"2024-07-05","cited_by_count":3,"area":"offlinerl"},{"id":"2408.01384","title":"NOLO: Navigate Only Look Once","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2601.22714","title":"Vision-Language Models Unlock Task-Centric Latent Actions","created":"2026-01-30","cited_by_count":3,"area":"mllm"},{"id":"2602.01960","title":"Grounding Generated Videos in Feasible Plans via World Models","created":"2026-02-02","cited_by_count":3,"area":"wm"},{"id":"2607.09185","title":"Causally Debiased Latent Action Model for Embodied Action Conditioned World Models","created":"2026-07-10","cited_by_count":3,"area":"wm"},{"id":"2008.01205","title":"Concurrent Training Improves the Performance of Behavioral Cloning from Observation","created":"2020-08-03","cited_by_count":2,"area":"offlinerl"},{"id":"2210.07658","title":"Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization","created":"2022-10-14","cited_by_count":2,"area":null},{"id":"2409.03996","title":"Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal Guidance","created":"2024-09-06","cited_by_count":2,"area":null},{"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":"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":"2605.12167","title":"From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2606.23420","title":"Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation","created":"2026-06-22","cited_by_count":2,"area":"diffusion"},{"id":"2011.02671","title":"HILONet: Hierarchical Imitation Learning from Non-Aligned Observations","created":"2020-11-05","cited_by_count":1,"area":"offlinerl"},{"id":"2305.19111","title":"GAN-MPC: Training Model Predictive Controllers with Parameterized Cost Functions using Demonstrations from Non-identical Experts","created":"2023-05-30","cited_by_count":1,"area":null},{"id":"2506.10085","title":"VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision-Language Models","created":"2025-06-11","cited_by_count":1,"area":"lr"},{"id":"2511.00555","title":"Improving Robustness to Out-of-Distribution States in Imitation Learning via Deep Koopman-Boosted Diffusion Policy","created":"2025-11-01","cited_by_count":1,"area":"diffusion"},{"id":"2602.02762","title":"On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning","created":"2026-02-02","cited_by_count":1,"area":"offlinerl"},{"id":"2606.19408","title":"FlexLAM: Resolving the Bottleneck Trade-off in Latent Action Learning","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2107.14613","title":"Incorporation of Deep Neural Network & Reinforcement Learning with Domain Knowledge","created":"2021-07-29","cited_by_count":0,"area":null},{"id":"2209.04100","title":"Task-Agnostic Learning to Accomplish New Tasks","created":"2022-09-09","cited_by_count":0,"area":"offlinerl"},{"id":"2211.01724","title":"Learning Control by Iterative Inversion","created":"2022-11-03","cited_by_count":0,"area":null},{"id":"2402.18836","title":"A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations","created":"2024-02-29","cited_by_count":0,"area":"deeprl"},{"id":"2509.19379","title":"Learning from Observation: A Survey of Recent Advances","created":"2025-09-20","cited_by_count":0,"area":"offlinerl"},{"id":"2603.17577","title":"Identifying Latent Actions and Dynamics from Offline Data via Demonstrator Diversity","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2605.14211","title":"ASH: Agents that Self-Hone in Long-Horizon Worlds","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.29416","title":"3DVLA: Enhancing Vision-Language-Action Models via 3D Spatial and Instance Understanding","created":"2026-05-28","cited_by_count":0,"area":"vla"},{"id":"2606.18223","title":"Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents","created":"2026-06-16","cited_by_count":0,"area":"deeprl"},{"id":"2607.04714","title":"Geometry-Aware Motion Latents for Learning Robust Manipulation Policies","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.19889","title":"Latent-Action-Guided Video-Language Feature Learning for Surgical Instrument-Tissue Interaction Recognition","created":"2026-07-22","cited_by_count":0,"area":null}],"next_cursor":"100"}