{"total":103,"rows":[{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912,"area":"alignment"},{"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":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459,"area":"offlinerl"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287,"area":null},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162,"area":"offlinerl"},{"id":"2112.01511","title":"The Surprising Effectiveness of Representation Learning for Visual Imitation","created":"2021-12-02","cited_by_count":154,"area":"offlinerl"},{"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":"2106.03911","title":"XIRL: Cross-embodiment Inverse Reinforcement Learning","created":"2021-06-07","cited_by_count":107,"area":"offlinerl"},{"id":"1807.09936","title":"Multi-Agent Generative Adversarial Imitation Learning","created":"2018-07-26","cited_by_count":100,"area":"offlinerl"},{"id":"1905.13566","title":"Recent Advances in Imitation Learning from Observation","created":"2019-05-30","cited_by_count":93,"area":"offlinerl"},{"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":"2201.12716","title":"You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration","created":"2022-01-30","cited_by_count":81,"area":null},{"id":"1806.01946","title":"Learning to Understand Goal Specifications by Modelling Reward","created":"2018-06-05","cited_by_count":80,"area":"alignment"},{"id":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71,"area":"alignment"},{"id":"2102.13185","title":"Off-Policy Imitation Learning from Observations","created":"2021-02-25","cited_by_count":70,"area":"offlinerl"},{"id":"2304.04782","title":"Reinforcement Learning from Passive Data via Latent Intentions","created":"2023-04-10","cited_by_count":68,"area":null},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58,"area":"offlinerl"},{"id":"2204.02320","title":"Learning Generalizable Dexterous Manipulation from Human Grasp Affordance","created":"2022-04-05","cited_by_count":51,"area":"offlinerl"},{"id":"2110.03684","title":"Cross-Domain Imitation Learning via Optimal Transport","created":"2021-10-07","cited_by_count":49,"area":"offlinerl"},{"id":"1910.04417","title":"Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement","created":"2019-10-10","cited_by_count":46,"area":"offlinerl"},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"1910.01077","title":"Task-Relevant Adversarial Imitation Learning","created":"2019-10-02","cited_by_count":45,"area":"offlinerl"},{"id":"2105.10037","title":"Cross-domain Imitation from Observations","created":"2021-05-20","cited_by_count":42,"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":"1911.00459","title":"Positive-Unlabeled Reward Learning","created":"2019-11-01","cited_by_count":37,"area":"alignment"},{"id":"2103.05115","title":"Deep reinforcement learning in medical imaging: A literature review","created":"2021-03-05","cited_by_count":34,"area":null},{"id":"1810.11043","title":"One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks","created":"2018-10-25","cited_by_count":33,"area":"offlinerl"},{"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":"2210.06518","title":"Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories","created":"2022-10-12","cited_by_count":28,"area":"offlinerl"},{"id":"1810.10593","title":"Inverse reinforcement learning for video games","created":"2018-10-24","cited_by_count":26,"area":"offlinerl"},{"id":"2102.07024","title":"Interactive Learning from Activity Description","created":"2021-02-13","cited_by_count":26,"area":null},{"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":"2106.05966","title":"Learning by Watching","created":"2021-06-10","cited_by_count":22,"area":"driving"},{"id":"2103.05079","title":"Domain-Robust Visual Imitation Learning with Mutual Information Constraints","created":"2021-03-08","cited_by_count":20,"area":"offlinerl"},{"id":"1912.03553","title":"Learning Norms from Stories: A Prior for Value Aligned Agents","created":"2019-12-07","cited_by_count":19,"area":"alignment"},{"id":"2406.01968","title":"Cross-Embodiment Robot Manipulation Skill Transfer using Latent Space Alignment","created":"2024-06-04","cited_by_count":18,"area":null},{"id":"1905.12310","title":"Adversarial Imitation Learning from Incomplete Demonstrations","created":"2019-05-29","cited_by_count":16,"area":"offlinerl"},{"id":"2211.00539","title":"Dungeons and Data: A Large-Scale NetHack Dataset","created":"2022-11-01","cited_by_count":16,"area":"offlinerl"},{"id":"2307.00972","title":"MoVie: Visual Model-Based Policy Adaptation for View Generalization","created":"2023-07-03","cited_by_count":16,"area":null},{"id":"2402.04580","title":"A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents","created":"2024-02-07","cited_by_count":16,"area":null},{"id":"2404.19456","title":"A Survey of Imitation Learning Methods, Environments and Metrics","created":"2024-04-30","cited_by_count":16,"area":"offlinerl"},{"id":"2104.09469","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","created":"2021-04-19","cited_by_count":14,"area":null},{"id":"2108.07259","title":"APReL: A Library for Active Preference-based Reward Learning Algorithms","created":"2021-08-16","cited_by_count":14,"area":null},{"id":"2209.12093","title":"Learn what matters: cross-domain imitation learning with task-relevant embeddings","created":"2022-09-24","cited_by_count":14,"area":"offlinerl"},{"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":"1909.12971","title":"Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation","created":"2019-09-27","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":"2107.09046","title":"Playful Interactions for Representation Learning","created":"2021-07-19","cited_by_count":13,"area":"offlinerl"},{"id":"2206.11895","title":"Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space","created":"2022-06-23","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":"2309.17371","title":"Adversarial Imitation Learning from Visual Observations using Latent Information","created":"2023-09-29","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":"2402.07127","title":"Learning by Watching: A Review of Video-based Learning Approaches for Robot Manipulation","created":"2024-02-11","cited_by_count":11,"area":null},{"id":"2202.00243","title":"Adversarial Imitation Learning from Video using a State Observer","created":"2022-02-01","cited_by_count":10,"area":"offlinerl"},{"id":"2306.10695","title":"SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models","created":"2023-06-19","cited_by_count":10,"area":"offlinerl"},{"id":"2202.11960","title":"All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL","created":"2022-02-24","cited_by_count":9,"area":"offlinerl"},{"id":"2210.00066","title":"Improving Policy Learning via Language Dynamics Distillation","created":"2022-09-30","cited_by_count":9,"area":null},{"id":"2407.12792","title":"Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learning","created":"2024-06-18","cited_by_count":9,"area":"offlinerl"},{"id":"2409.08687","title":"xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing","created":"2024-09-13","cited_by_count":9,"area":"diffusion"},{"id":"2109.05940","title":"Cross Domain Robot Imitation with Invariant Representation","created":"2021-09-13","cited_by_count":8,"area":"offlinerl"},{"id":"2507.12496","title":"FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making","created":"2025-07-15","cited_by_count":8,"area":"wm"},{"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":"2303.07026","title":"Visual-Policy Learning through Multi-Camera View to Single-Camera View Knowledge Distillation for Robot Manipulation Tasks","created":"2023-03-13","cited_by_count":7,"area":"distill"},{"id":"1906.07374","title":"Sample-efficient Adversarial Imitation Learning from Observation","created":"2019-06-18","cited_by_count":6,"area":"offlinerl"},{"id":"1910.00105","title":"Domain Adaptive Imitation Learning","created":"2019-09-30","cited_by_count":6,"area":"offlinerl"},{"id":"1911.05864","title":"Motion Reasoning for Goal-Based Imitation Learning","created":"2019-11-13","cited_by_count":6,"area":"offlinerl"},{"id":"2008.12647","title":"ADAIL: Adaptive Adversarial Imitation Learning","created":"2020-08-23","cited_by_count":6,"area":"offlinerl"},{"id":"2505.09040","title":"RT-Cache: Training-Free Retrieval for Real-Time Manipulation","created":"2025-05-14","cited_by_count":6,"area":null},{"id":"2104.07810","title":"Skeletal Feature Compensation for Imitation Learning with Embodiment Mismatch","created":"2021-04-15","cited_by_count":5,"area":"offlinerl"},{"id":"2202.13604","title":"Generalizable task representation learning from human demonstration videos: a geometric approach","created":"2022-02-28","cited_by_count":5,"area":null},{"id":"2206.00238","title":"Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble","created":"2022-06-01","cited_by_count":5,"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":"2106.09256","title":"Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning","created":"2021-06-17","cited_by_count":4,"area":"offlinerl"},{"id":"2404.07735","title":"Diffusing in Someone Else's Shoes: Robotic Perspective Taking with Diffusion","created":"2024-04-11","cited_by_count":4,"area":null},{"id":"1805.04969","title":"Learning Temporal Strategic Relationships using Generative Adversarial Imitation Learning","created":"2018-05-13","cited_by_count":3,"area":"offlinerl"},{"id":"2103.15171","title":"A Bayesian Approach to Identifying Representational Errors","created":"2021-03-28","cited_by_count":2,"area":null},{"id":"2104.06600","title":"GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback","created":"2021-04-14","cited_by_count":2,"area":"offlinerl"},{"id":"2404.03382","title":"DIDA: Denoised Imitation Learning based on Domain Adaptation","created":"2024-04-04","cited_by_count":2,"area":"offlinerl"},{"id":"2502.09029","title":"MTDP: A Modulated Transformer based Diffusion Policy Model","created":"2025-02-13","cited_by_count":2,"area":"diffusion"},{"id":"2505.12204","title":"Of Mice and Machines: A Comparison of Learning Between Real World Mice and RL Agents","created":"2025-05-18","cited_by_count":2,"area":"deeprl"},{"id":"2006.01494","title":"Cross-Domain Imitation Learning with a Dual Structure","created":"2020-06-02","cited_by_count":1,"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":"2202.05135","title":"Group-Agent Reinforcement Learning","created":"2022-02-10","cited_by_count":1,"area":null},{"id":"2206.11004","title":"Auto-Encoding Adversarial Imitation Learning","created":"2022-06-22","cited_by_count":1,"area":"offlinerl"},{"id":"2312.16365","title":"Active Third-Person Imitation Learning","created":"2023-12-27","cited_by_count":1,"area":"offlinerl"},{"id":"2404.03386","title":"SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring","created":"2024-04-04","cited_by_count":1,"area":"offlinerl"},{"id":"2407.16912","title":"Cross-Domain Policy Transfer by Representation Alignment via Multi-Domain Behavioral Cloning","created":"2024-07-24","cited_by_count":1,"area":"offlinerl"},{"id":"2505.18899","title":"Beyond Domain Randomization: Event-Inspired Perception for Visually Robust Adversarial Imitation from Videos","created":"2025-05-24","cited_by_count":1,"area":null},{"id":"2512.17899","title":"Distributionally Robust Imitation Learning: Layered Control Architecture for Certifiable Autonomy","created":"2025-12-19","cited_by_count":1,"area":"offlinerl"},{"id":"2211.14469","title":"Transfer RL via the Undo Maps Formalism","created":"2022-11-26","cited_by_count":0,"area":null},{"id":"2212.06048","title":"Machine Learning Approaches for Principle Prediction in Naturally Occurring Stories","created":"2022-11-19","cited_by_count":0,"area":null},{"id":"2302.13124","title":"Simulation of robot swarms for learning communication-aware coordination","created":"2023-02-25","cited_by_count":0,"area":null},{"id":"2306.00975","title":"Active Vision Reinforcement Learning under Limited Visual Observability","created":"2023-06-01","cited_by_count":0,"area":null},{"id":"2310.00964","title":"All by Myself: Learning Individualized Competitive Behaviour with a Contrastive Reinforcement Learning optimization","created":"2023-10-02","cited_by_count":0,"area":null},{"id":"2501.09707","title":"The Goofus & Gallant Story Corpus for Practical Value Alignment","created":"2025-01-16","cited_by_count":0,"area":null},{"id":"2509.19379","title":"Learning from Observation: A Survey of Recent Advances","created":"2025-09-20","cited_by_count":0,"area":"offlinerl"},{"id":"2512.05335","title":"State-Conditional Adversarial Learning: An Off-Policy Visual Domain Transfer Method for End-to-End Imitation Learning","created":"2025-12-05","cited_by_count":0,"area":"offlinerl"},{"id":"2601.00452","title":"Imitation from Observations with Trajectory-Level Generative Embeddings","created":"2026-01-01","cited_by_count":0,"area":"offlinerl"}],"next_cursor":"100"}