{"total":93,"rows":[{"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":"2310.08576","title":"Learning to Act from Actionless Videos through Dense Correspondences","created":"2023-10-12","cited_by_count":164,"area":null},{"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":"2312.10812","title":"Learning to Act without Actions","created":"2023-12-17","cited_by_count":121,"area":"wm"},{"id":"2202.00164","title":"DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video","created":"2022-02-01","cited_by_count":89,"area":null},{"id":"2303.01497","title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","created":"2023-03-02","cited_by_count":75,"area":"offlinerl"},{"id":"2102.13185","title":"Off-Policy Imitation Learning from Observations","created":"2021-02-25","cited_by_count":70,"area":"offlinerl"},{"id":"2206.15469","title":"Watch and Match: Supercharging Imitation with Regularized Optimal Transport","created":"2022-06-30","cited_by_count":67,"area":"offlinerl"},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58,"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":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"area":null},{"id":"2301.05832","title":"World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges","created":"2023-01-14","cited_by_count":36,"area":"wm"},{"id":"2509.02722","title":"Planning with Reasoning using Vision Language World Model","created":"2025-09-02","cited_by_count":36,"area":"wm"},{"id":"2309.12300","title":"See to Touch: Learning Tactile Dexterity through Visual Incentives","created":"2023-09-21","cited_by_count":35,"area":null},{"id":"2408.04380","title":"Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations","created":"2024-08-08","cited_by_count":35,"area":"offlinerl"},{"id":"2304.08487","title":"Hyper-Decision Transformer for Efficient Online Policy Adaptation","created":"2023-04-17","cited_by_count":33,"area":"offlinerl"},{"id":"2404.14735","title":"Rank2Reward: Learning Shaped Reward Functions from Passive Video","created":"2024-04-23","cited_by_count":32,"area":"deeprl"},{"id":"2105.09371","title":"VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigation","created":"2021-05-19","cited_by_count":31,"area":"offlinerl"},{"id":"2008.09167","title":"Imitation Learning with Sinkhorn Distances","created":"2020-08-20","cited_by_count":30,"area":"offlinerl"},{"id":"2303.00599","title":"LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning","created":"2023-03-01","cited_by_count":29,"area":"offlinerl"},{"id":"2210.06518","title":"Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories","created":"2022-10-12","cited_by_count":28,"area":"offlinerl"},{"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":"2410.10076","title":"VideoAgent: Self-Improving Video Generation","created":"2024-10-14","cited_by_count":25,"area":null},{"id":"2103.05079","title":"Domain-Robust Visual Imitation Learning with Mutual Information Constraints","created":"2021-03-08","cited_by_count":20,"area":"offlinerl"},{"id":"2202.03481","title":"A Ranking Game for Imitation Learning","created":"2022-02-07","cited_by_count":18,"area":"offlinerl"},{"id":"2204.10320","title":"SelfD: Self-Learning Large-Scale Driving Policies From the Web","created":"2022-04-21","cited_by_count":18,"area":"driving"},{"id":"2303.17156","title":"MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations","created":"2023-03-30","cited_by_count":18,"area":"offlinerl"},{"id":"2411.09891","title":"Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation","created":"2024-11-15","cited_by_count":17,"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":"2412.06784","title":"P3-PO: Prescriptive Point Priors for Visuo-Spatial Generalization of Robot Policies","created":"2024-12-09","cited_by_count":16,"area":null},{"id":"2402.03807","title":"SEABO: A Simple Search-Based Method for Offline Imitation Learning","created":"2024-02-06","cited_by_count":14,"area":"offlinerl"},{"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":"2203.02214","title":"Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization","created":"2022-03-04","cited_by_count":12,"area":"offlinerl"},{"id":"2502.13900","title":"Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning","created":"2025-02-19","cited_by_count":12,"area":"offlinerl"},{"id":"2002.04306","title":"Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learning","created":"2020-02-11","cited_by_count":10,"area":"offlinerl"},{"id":"2202.00243","title":"Adversarial Imitation Learning from Video using a State Observer","created":"2022-02-01","cited_by_count":10,"area":"offlinerl"},{"id":"2210.17178","title":"Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning","created":"2022-10-31","cited_by_count":10,"area":"offlinerl"},{"id":"2303.13800","title":"Aligning Step-by-Step Instructional Diagrams to Video Demonstrations","created":"2023-03-24","cited_by_count":10,"area":null},{"id":"2310.07433","title":"Imitation Learning from Observation with Automatic Discount Scheduling","created":"2023-10-11","cited_by_count":10,"area":"offlinerl"},{"id":"2403.13765","title":"Towards Principled Representation Learning from Videos for Reinforcement Learning","created":"2024-03-20","cited_by_count":10,"area":"deeprl"},{"id":"2411.07007","title":"Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching","created":"2024-11-11","cited_by_count":10,"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":"2407.18178","title":"PianoMime: Learning a Generalist, Dexterous Piano Player from Internet Demonstrations","created":"2024-07-25","cited_by_count":9,"area":null},{"id":"2207.01845","title":"Planning with RL and episodic-memory behavioral priors","created":"2022-07-05","cited_by_count":8,"area":null},{"id":"2304.03833","title":"Learning Robot Manipulation from Cross-Morphology Demonstration","created":"2023-04-07","cited_by_count":8,"area":"offlinerl"},{"id":"2001.11628","title":"Domain-Adversarial and Conditional State Space Model for Imitation Learning","created":"2020-01-31","cited_by_count":7,"area":"offlinerl"},{"id":"1906.07374","title":"Sample-efficient Adversarial Imitation Learning from Observation","created":"2019-06-18","cited_by_count":6,"area":"offlinerl"},{"id":"2202.04332","title":"Imitation Learning by State-Only Distribution Matching","created":"2022-02-09","cited_by_count":6,"area":"offlinerl"},{"id":"2008.13193","title":"Learn by Observation: Imitation Learning for Drone Patrolling from Videos of A Human Navigator","created":"2020-08-30","cited_by_count":5,"area":"offlinerl"},{"id":"2210.04251","title":"State Advantage Weighting for Offline RL","created":"2022-10-09","cited_by_count":5,"area":"offlinerl"},{"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":"1909.00895","title":"Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data","created":"2019-09-03","cited_by_count":4,"area":"offlinerl"},{"id":"2104.00163","title":"DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation","created":"2021-03-31","cited_by_count":4,"area":"offlinerl"},{"id":"2207.02087","title":"Learning to Accelerate Approximate Methods for Solving Integer Programming via Early Fixing","created":"2022-07-05","cited_by_count":3,"area":null},{"id":"2303.01440","title":"Programmatic Imitation Learning from Unlabeled and Noisy Demonstrations","created":"2023-03-02","cited_by_count":3,"area":"offlinerl"},{"id":"2312.15474","title":"A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learning","created":"2023-12-24","cited_by_count":3,"area":null},{"id":"2401.16452","title":"Context-Former: Stitching via Latent Conditioned Sequence Modeling","created":"2024-01-29","cited_by_count":3,"area":"offlinerl"},{"id":"2407.20917","title":"How to Choose a Reinforcement-Learning Algorithm","created":"2024-07-30","cited_by_count":3,"area":"deeprl"},{"id":"2501.14856","title":"Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation","created":"2025-01-24","cited_by_count":3,"area":"offlinerl"},{"id":"2601.22714","title":"Vision-Language Models Unlock Task-Centric Latent Actions","created":"2026-01-30","cited_by_count":3,"area":"mllm"},{"id":"2602.06769","title":"Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities","created":"2026-02-06","cited_by_count":3,"area":"deeprl"},{"id":"2210.14428","title":"D-Shape: Demonstration-Shaped Reinforcement Learning via Goal Conditioning","created":"2022-10-26","cited_by_count":2,"area":"offlinerl"},{"id":"2409.02724","title":"Surgical Task Automation Using Actor-Critic Frameworks and Self-Supervised Imitation Learning","created":"2024-09-04","cited_by_count":2,"area":"offlinerl"},{"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":"2507.21533","title":"Model Predictive Adversarial Imitation Learning for Planning from Observation","created":"2025-07-29","cited_by_count":2,"area":"offlinerl"},{"id":"2510.09325","title":"Rate optimal learning of equilibria from data","created":"2025-10-10","cited_by_count":2,"area":"offlinerl"},{"id":"2011.02671","title":"HILONet: Hierarchical Imitation Learning from Non-Aligned Observations","created":"2020-11-05","cited_by_count":1,"area":"offlinerl"},{"id":"2302.06540","title":"Imitation from Observation With Bootstrapped Contrastive Learning","created":"2023-02-13","cited_by_count":1,"area":null},{"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":"2309.01784","title":"INTAGS: Interactive Agent-Guided Simulation","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2312.16365","title":"Active Third-Person Imitation Learning","created":"2023-12-27","cited_by_count":1,"area":"offlinerl"},{"id":"2404.08791","title":"Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch","created":"2024-04-12","cited_by_count":1,"area":"alignment"},{"id":"2601.07516","title":"Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions","created":"2026-01-12","cited_by_count":1,"area":"mllm"},{"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":"2202.09271","title":"Enhanced Behavioral Cloning with Environmental Losses for Self-Driving Vehicles","created":"2022-02-04","cited_by_count":0,"area":"driving"},{"id":"2209.04100","title":"Task-Agnostic Learning to Accomplish New Tasks","created":"2022-09-09","cited_by_count":0,"area":"offlinerl"},{"id":"2304.12432","title":"Generative Adversarial Neuroevolution for Control Behaviour Imitation","created":"2023-04-03","cited_by_count":0,"area":"offlinerl"},{"id":"2306.04581","title":"Divide and Repair: Using Options to Improve Performance of Imitation Learning Against Adversarial Demonstrations","created":"2023-06-07","cited_by_count":0,"area":"offlinerl"},{"id":"2311.15399","title":"Optimally Teaching a Linear Behavior Cloning Agent","created":"2023-11-26","cited_by_count":0,"area":null},{"id":"2405.20351","title":"Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression","created":"2024-05-28","cited_by_count":0,"area":"offlinerl"},{"id":"2408.05610","title":"Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrations","created":"2024-08-10","cited_by_count":0,"area":"alignment"},{"id":"2412.07617","title":"Swarm Behavior Cloning","created":"2024-12-10","cited_by_count":0,"area":"offlinerl"},{"id":"2501.12785","title":"On Generalization and Distributional Update for Mimicking Observations with Adequate Exploration","created":"2025-01-22","cited_by_count":0,"area":"offlinerl"},{"id":"2501.14942","title":"Force-Based Robotic Imitation Learning: A Two-Phase Approach for Construction Assembly Tasks","created":"2025-01-24","cited_by_count":0,"area":null},{"id":"2502.15262","title":"Towards a Reward-Free Reinforcement Learning Framework for Vehicle Control","created":"2025-02-21","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":"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":"2511.03616","title":"Going Beyond Expert Performance via Deep Implicit Imitation Reinforcement Learning","created":"2025-11-05","cited_by_count":0,"area":"offlinerl"},{"id":"2605.12224","title":"Intrinsic Vicarious Conditioning for Deep Reinforcement Learning","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2607.13436","title":"Distributionally Robust and Safe Imitation Learning","created":"2026-07-15","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}