{"total":1597,"rows":[{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912,"area":"alignment"},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114,"area":"diffusion"},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055,"area":"alignment"},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657,"area":"offlinerl"},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571,"area":"alignment"},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557,"area":"synth"},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492,"area":"offlinerl"},{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490,"area":"driving"},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459,"area":"offlinerl"},{"id":"2109.00137","title":"Implicit Behavioral Cloning","created":"2021-09-01","cited_by_count":452,"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":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442,"area":null},{"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":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327,"area":null},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316,"area":"alignment"},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304,"area":"offlinerl"},{"id":"1806.06877","title":"A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress","created":"2018-06-18","cited_by_count":298,"area":"offlinerl"},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288,"area":"offlinerl"},{"id":"2402.10885","title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","created":"2024-02-16","cited_by_count":282,"area":"diffusion"},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2301.10677","title":"Imitating Human Behaviour with Diffusion Models","created":"2023-01-25","cited_by_count":263,"area":"diffusion"},{"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":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2109.13396","title":"Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets","created":"2021-09-27","cited_by_count":250,"area":null},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247,"area":"alignment"},{"id":"2601.19897","title":"Self-Distillation Enables Continual Learning","created":"2026-01-27","cited_by_count":247,"area":"offlinerl"},{"id":"2304.02532","title":"Goal-Conditioned Imitation Learning using Score-based Diffusion Policies","created":"2023-04-05","cited_by_count":236,"area":"diffusion"},{"id":"2102.04942","title":"Robust Motion In-betweening","created":"2021-02-09","cited_by_count":229,"area":null},{"id":"2005.07648","title":"Language Conditioned Imitation Learning over Unstructured Data","created":"2020-05-15","cited_by_count":209,"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":"1809.02925","title":"Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning","created":"2018-09-09","cited_by_count":204,"area":"offlinerl"},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197,"area":null},{"id":"2108.08265","title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","created":"2021-08-18","cited_by_count":194,"area":"driving"},{"id":"2101.06557","title":"TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors","created":"2021-01-17","cited_by_count":193,"area":null},{"id":"2106.12142","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","created":"2021-06-23","cited_by_count":193,"area":"offlinerl"},{"id":"1911.02256","title":"A Divergence Minimization Perspective on Imitation Learning Methods","created":"2019-11-06","cited_by_count":190,"area":"offlinerl"},{"id":"2112.10751","title":"RvS: What is Essential for Offline RL via Supervised Learning?","created":"2021-12-20","cited_by_count":185,"area":"offlinerl"},{"id":"1912.05032","title":"Imitation Learning via Off-Policy Distribution Matching","created":"2019-12-10","cited_by_count":183,"area":"offlinerl"},{"id":"2209.14548","title":"Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling","created":"2022-09-29","cited_by_count":182,"area":"offlinerl"},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162,"area":"offlinerl"},{"id":"2403.03181","title":"Behavior Generation with Latent Actions","created":"2024-03-05","cited_by_count":160,"area":"diffusion"},{"id":"2402.03681","title":"RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback","created":"2024-02-06","cited_by_count":156,"area":"mllm"},{"id":"2203.03580","title":"The Unsurprising Effectiveness of Pre-Trained Vision Models for Control","created":"2022-03-07","cited_by_count":155,"area":null},{"id":"2101.11517","title":"Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond","created":"2021-01-27","cited_by_count":153,"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":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143,"area":null},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142,"area":"mllm"},{"id":"2310.07899","title":"RoboCLIP: One Demonstration is Enough to Learn Robot Policies","created":"2023-10-11","cited_by_count":134,"area":"offlinerl"},{"id":"2011.07213","title":"PLAS: Latent Action Space for Offline Reinforcement Learning","created":"2020-11-14","cited_by_count":133,"area":"offlinerl"},{"id":"2212.11419","title":"Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios","created":"2022-12-21","cited_by_count":129,"area":"driving"},{"id":"1802.09564","title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills","created":"2018-02-26","cited_by_count":126,"area":"offlinerl"},{"id":"2305.01649","title":"Generalizing Dataset Distillation via Deep Generative Prior","created":"2023-05-02","cited_by_count":126,"area":null},{"id":"1905.12888","title":"Imitation Learning as $f$-Divergence Minimization","created":"2019-05-30","cited_by_count":123,"area":"offlinerl"},{"id":"2106.12534","title":"Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation","created":"2021-06-23","cited_by_count":122,"area":null},{"id":"2109.13333","title":"Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients","created":"2021-09-27","cited_by_count":122,"area":"driving"},{"id":"2006.04678","title":"Primal Wasserstein Imitation Learning","created":"2020-06-08","cited_by_count":121,"area":"offlinerl"},{"id":"2103.17138","title":"SOON: Scenario Oriented Object Navigation with Graph-based Exploration","created":"2021-03-31","cited_by_count":119,"area":null},{"id":"1901.09387","title":"Imitation Learning from Imperfect Demonstration","created":"2019-01-27","cited_by_count":114,"area":"offlinerl"},{"id":"2104.00683","title":"SimPoE: Simulated Character Control for 3D Human Pose Estimation","created":"2021-04-01","cited_by_count":114,"area":null},{"id":"2303.09824","title":"Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives","created":"2023-03-17","cited_by_count":114,"area":"driving"},{"id":"2012.06733","title":"Human-in-the-Loop Imitation Learning using Remote Teleoperation","created":"2020-12-12","cited_by_count":112,"area":"offlinerl"},{"id":"2109.08273","title":"ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning","created":"2021-09-17","cited_by_count":108,"area":"offlinerl"},{"id":"2106.03911","title":"XIRL: Cross-embodiment Inverse Reinforcement Learning","created":"2021-06-07","cited_by_count":107,"area":"offlinerl"},{"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":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106,"area":"offlinerl"},{"id":"1810.00821","title":"Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow","created":"2018-10-01","cited_by_count":105,"area":"offlinerl"},{"id":"2302.00883","title":"Synthesizing Physical Character-Scene Interactions","created":"2023-02-02","cited_by_count":104,"area":null},{"id":"2403.04133","title":"Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving","created":"2024-03-07","cited_by_count":104,"area":"driving"},{"id":"2210.10047","title":"From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data","created":"2022-10-18","cited_by_count":103,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"1807.09936","title":"Multi-Agent Generative Adversarial Imitation Learning","created":"2018-07-26","cited_by_count":100,"area":"offlinerl"},{"id":"2009.05990","title":"Toward the Fundamental Limits of Imitation Learning","created":"2020-09-13","cited_by_count":96,"area":"offlinerl"},{"id":"2209.11178","title":"Poisson Flow Generative Models","created":"2022-09-22","cited_by_count":95,"area":null},{"id":"2209.04899","title":"Instruction-driven history-aware policies for robotic manipulations","created":"2022-09-11","cited_by_count":94,"area":null},{"id":"2305.02195","title":"CALM: Conditional Adversarial Latent Models for Directable Virtual Characters","created":"2023-05-02","cited_by_count":94,"area":null},{"id":"1905.13566","title":"Recent Advances in Imitation Learning from Observation","created":"2019-05-30","cited_by_count":93,"area":"offlinerl"},{"id":"2105.06411","title":"Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration","created":"2021-05-13","cited_by_count":93,"area":"offlinerl"},{"id":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93,"area":null},{"id":"2004.04650","title":"State-Only Imitation Learning for Dexterous Manipulation","created":"2020-04-07","cited_by_count":91,"area":"offlinerl"},{"id":"2401.03360","title":"Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models","created":"2023-10-13","cited_by_count":91,"area":"diffusion"},{"id":"2203.15103","title":"Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions","created":"2022-03-28","cited_by_count":89,"area":null},{"id":"2207.10050","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","created":"2022-07-20","cited_by_count":89,"area":"offlinerl"},{"id":"2105.14829","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","created":"2021-05-31","cited_by_count":85,"area":null},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"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":"2103.03236","title":"Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap","created":"2021-03-04","cited_by_count":81,"area":"offlinerl"},{"id":"2205.11140","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","created":"2022-05-23","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":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80,"area":null},{"id":"1905.10948","title":"Provably Efficient Imitation Learning from Observation Alone","created":"2019-05-27","cited_by_count":78,"area":"offlinerl"},{"id":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76,"area":null},{"id":"2312.04393","title":"PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction","created":"2023-12-07","cited_by_count":76,"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":"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":"2207.10422","title":"Differentiable Integrated Motion Prediction and Planning with Learnable Cost Function for Autonomous Driving","created":"2022-07-21","cited_by_count":73,"area":"driving"},{"id":"2011.13885","title":"Offline Learning from Demonstrations and Unlabeled Experience","created":"2020-11-27","cited_by_count":72,"area":"offlinerl"},{"id":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71,"area":"alignment"}],"next_cursor":"100"}