{"total":99,"rows":[{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"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":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260,"area":"offlinerl"},{"id":"2108.05877","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","created":"2021-08-12","cited_by_count":206,"area":"offlinerl"},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","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":"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":"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":"2204.12490","title":"From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation","created":"2022-04-26","cited_by_count":82,"area":"offlinerl"},{"id":"1911.10947","title":"State Alignment-based Imitation Learning","created":"2019-11-21","cited_by_count":73,"area":"offlinerl"},{"id":"2002.09089","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","created":"2020-02-21","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":"2412.13630","title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model","created":"2024-12-18","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":"2204.02320","title":"Learning Generalizable Dexterous Manipulation from Human Grasp Affordance","created":"2022-04-05","cited_by_count":51,"area":"offlinerl"},{"id":"2302.02011","title":"Zero-Shot Robot Manipulation from Passive Human Videos","created":"2023-02-03","cited_by_count":51,"area":null},{"id":"2110.03684","title":"Cross-Domain Imitation Learning via Optimal Transport","created":"2021-10-07","cited_by_count":49,"area":"offlinerl"},{"id":"2110.13423","title":"Towards More Generalizable One-shot Visual Imitation Learning","created":"2021-10-26","cited_by_count":49,"area":"offlinerl"},{"id":"2207.14299","title":"Graph Inverse Reinforcement Learning from Diverse Videos","created":"2022-07-28","cited_by_count":46,"area":"offlinerl"},{"id":"2403.12014","title":"EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents","created":"2024-03-18","cited_by_count":46,"area":"agents"},{"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":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","cited_by_count":44,"area":"offlinerl"},{"id":"2210.02019","title":"Atari-5: Distilling the Arcade Learning Environment down to Five Games","created":"2022-10-05","cited_by_count":44,"area":null},{"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":"2106.09678","title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies","created":"2021-06-17","cited_by_count":43,"area":null},{"id":"2310.08235","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","created":"2023-10-12","cited_by_count":42,"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":"2102.10960","title":"Return-Based Contrastive Representation Learning for Reinforcement Learning","created":"2021-02-22","cited_by_count":36,"area":null},{"id":"2105.12272","title":"Provable Representation Learning for Imitation with Contrastive Fourier Features","created":"2021-05-26","cited_by_count":34,"area":"offlinerl"},{"id":"2305.16985","title":"Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation","created":"2023-05-26","cited_by_count":31,"area":null},{"id":"2209.08890","title":"An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey","created":"2022-09-19","cited_by_count":28,"area":null},{"id":"2402.14795","title":"CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation","created":"2024-02-22","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":"1811.03516","title":"Learning from Demonstration in the Wild","created":"2018-11-08","cited_by_count":25,"area":"offlinerl"},{"id":"2206.05314","title":"Large-Scale Retrieval for Reinforcement Learning","created":"2022-06-10","cited_by_count":24,"area":"offlinerl"},{"id":"1905.09335","title":"Imitation Learning from Video by Leveraging Proprioception","created":"2019-05-22","cited_by_count":23,"area":"offlinerl"},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","cited_by_count":23,"area":null},{"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":"2110.13578","title":"Distributional Reinforcement Learning for Multi-Dimensional Reward Functions","created":"2021-10-26","cited_by_count":22,"area":null},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2405.16194","title":"Diffusion-Reward Adversarial Imitation Learning","created":"2024-05-25","cited_by_count":20,"area":"diffusion"},{"id":"2106.04480","title":"There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2110.07692","title":"Shaping embodied agent behavior with activity-context priors from egocentric video","created":"2021-10-14","cited_by_count":17,"area":null},{"id":"2110.14118","title":"Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning","created":"2021-10-27","cited_by_count":17,"area":"offlinerl"},{"id":"2211.09019","title":"Learning Reward Functions for Robotic Manipulation by Observing Humans","created":"2022-11-16","cited_by_count":17,"area":null},{"id":"2305.00477","title":"Posterior Sampling for Deep Reinforcement Learning","created":"2023-04-30","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":"2208.12345","title":"Light-weight probing of unsupervised representations for Reinforcement Learning","created":"2022-08-25","cited_by_count":15,"area":null},{"id":"1904.01139","title":"Generative predecessor models for sample-efficient imitation learning","created":"2019-04-01","cited_by_count":14,"area":"offlinerl"},{"id":"2301.00810","title":"SIRL: Similarity-based Implicit Representation Learning","created":"2023-01-02","cited_by_count":14,"area":null},{"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":"2112.00597","title":"Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation","created":"2021-12-01","cited_by_count":13,"area":null},{"id":"2002.06473","title":"Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning","created":"2020-02-15","cited_by_count":12,"area":"offlinerl"},{"id":"2309.16973","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","created":"2023-09-29","cited_by_count":12,"area":"offlinerl"},{"id":"2104.06411","title":"Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning","created":"2021-04-13","cited_by_count":11,"area":null},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11,"area":null},{"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":"2503.01837","title":"Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning","created":"2025-03-03","cited_by_count":11,"area":"wm"},{"id":"2309.10790","title":"Guide Your Agent with Adaptive Multimodal Rewards","created":"2023-09-19","cited_by_count":10,"area":"offlinerl"},{"id":"2404.16779","title":"DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2505.22626","title":"SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning","created":"2025-05-28","cited_by_count":9,"area":"offlinerl"},{"id":"2212.00169","title":"Time-Efficient Reward Learning via Visually Assisted Cluster Ranking","created":"2022-11-30","cited_by_count":8,"area":"alignment"},{"id":"2601.12428","title":"ReWorld: Multi-Dimensional Reward Modeling for Embodied World Models","created":"2026-01-18","cited_by_count":8,"area":"wm"},{"id":"1909.03773","title":"Imitation Learning from Pixel-Level Demonstrations by HashReward","created":"2019-09-09","cited_by_count":6,"area":"offlinerl"},{"id":"2002.12500","title":"Efficiently Guiding Imitation Learning Agents with Human Gaze","created":"2020-02-28","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":"2103.06370","title":"Causal-aware Safe Policy Improvement for Task-oriented dialogue","created":"2021-03-10","cited_by_count":4,"area":null},{"id":"2402.13930","title":"Enhancing Reinforcement Learning Agents with Local Guides","created":"2024-02-21","cited_by_count":4,"area":"deeprl"},{"id":"2103.00098","title":"Reducing Conservativeness Oriented Offline Reinforcement Learning","created":"2021-02-27","cited_by_count":3,"area":"offlinerl"},{"id":"2103.03240","title":"Learning ABCs: Approximate Bijective Correspondence for isolating factors of variation with weak supervision","created":"2021-03-04","cited_by_count":3,"area":null},{"id":"2203.04303","title":"Policy Regularization for Legible Behavior","created":"2022-03-08","cited_by_count":3,"area":null},{"id":"2204.00888","title":"Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Tasks","created":"2022-04-02","cited_by_count":3,"area":null},{"id":"2408.01384","title":"NOLO: Navigate Only Look Once","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2106.05139","title":"Pretrained Encoders are All You Need","created":"2021-06-09","cited_by_count":2,"area":null},{"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":"2303.07046","title":"Deploying Offline Reinforcement Learning with Human Feedback","created":"2023-03-13","cited_by_count":2,"area":"alignment"},{"id":"2402.01057","title":"Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning","created":"2024-02-01","cited_by_count":2,"area":"offlinerl"},{"id":"2511.04137","title":"Learning from Online Videos at Inference Time for Computer-Use Agents","created":"2025-11-06","cited_by_count":2,"area":"agents"},{"id":"1810.01108","title":"Injective State-Image Mapping facilitates Visual Adversarial Imitation Learning","created":"2018-10-02","cited_by_count":1,"area":"offlinerl"},{"id":"2301.05635","title":"Time-Myopic Go-Explore: Learning A State Representation for the Go-Explore Paradigm","created":"2023-01-13","cited_by_count":1,"area":null},{"id":"2301.07182","title":"Genetic Imitation Learning by Reward Extrapolation","created":"2023-01-03","cited_by_count":1,"area":"offlinerl"},{"id":"2303.13489","title":"Boosting Reinforcement Learning and Planning with Demonstrations: A Survey","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2602.02799","title":"Joint Learning of Hierarchical Neural Options and Abstract World Model","created":"2026-02-02","cited_by_count":1,"area":"wm"},{"id":"2102.11762","title":"School of hard knocks: Curriculum analysis for Pommerman with a fixed computational budget","created":"2021-02-23","cited_by_count":0,"area":null},{"id":"2104.06163","title":"Reward Shaping with Dynamic Trajectory Aggregation","created":"2021-04-13","cited_by_count":0,"area":null},{"id":"2205.07882","title":"Aligning Robot Representations with Humans","created":"2022-05-15","cited_by_count":0,"area":"alignment"},{"id":"2312.10069","title":"Understanding Representations Pretrained with Auxiliary Losses for Embodied Agent Planning","created":"2023-12-06","cited_by_count":0,"area":"offlinerl"},{"id":"2410.18626","title":"SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance","created":"2024-10-24","cited_by_count":0,"area":"offlinerl"},{"id":"2410.23554","title":"Prosody as a Teaching Signal for Agent Learning: Exploratory Studies and Algorithmic Implications","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2503.13557","title":"APF+: Boosting adaptive-potential function reinforcement learning methods with a W-shaped network for high-dimensional games","created":"2025-03-17","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":"2509.24784","title":"Quantifying Generalisation in Imitation Learning","created":"2025-09-29","cited_by_count":0,"area":"offlinerl"},{"id":"2604.08475","title":"LAMP: Lift Image-Editing as General 3D Priors for Open-world Manipulation","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2610.14159","title":"Disentangling Task-Relevant Latent Dynamics for Reward Modeling","created":"2026-10-09","cited_by_count":0,"area":"alignment"}],"next_cursor":null}