{"total":492,"rows":[{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747,"area":"wm"},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"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":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327,"area":"lr"},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304,"area":"offlinerl"},{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302,"area":"agents"},{"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":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221,"area":null},{"id":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215,"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":"2503.10631","title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","created":"2025-03-13","cited_by_count":181,"area":"vla"},{"id":"2305.17390","title":"SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks","created":"2023-05-27","cited_by_count":168,"area":"lr"},{"id":"2310.08576","title":"Learning to Act from Actionless Videos through Dense Correspondences","created":"2023-10-12","cited_by_count":164,"area":null},{"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":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141,"area":null},{"id":"2306.08543","title":"MiniLLM: On-Policy Distillation of Large Language Models","created":"2023-06-14","cited_by_count":139,"area":"distill"},{"id":"1905.12888","title":"Imitation Learning as $f$-Divergence Minimization","created":"2019-05-30","cited_by_count":123,"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":"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":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102,"area":null},{"id":"2009.05990","title":"Toward the Fundamental Limits of Imitation Learning","created":"2020-09-13","cited_by_count":96,"area":"offlinerl"},{"id":"2209.04899","title":"Instruction-driven history-aware policies for robotic manipulations","created":"2022-09-11","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":"2403.08715","title":"SOTOPIA-$\\pi$: Interactive Learning of Socially Intelligent Language Agents","created":"2024-03-13","cited_by_count":93,"area":"agents"},{"id":"2004.04650","title":"State-Only Imitation Learning for Dexterous Manipulation","created":"2020-04-07","cited_by_count":91,"area":"offlinerl"},{"id":"2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","created":"2021-01-18","cited_by_count":87,"area":null},{"id":"2103.06326","title":"S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning","created":"2021-03-10","cited_by_count":85,"area":"offlinerl"},{"id":"2301.13362","title":"Optimizing DDPM Sampling with Shortcut Fine-Tuning","created":"2023-01-31","cited_by_count":81,"area":"diffusion"},{"id":"1905.10948","title":"Provably Efficient Imitation Learning from Observation Alone","created":"2019-05-27","cited_by_count":78,"area":"offlinerl"},{"id":"2305.14343","title":"Video Prediction Models as Rewards for Reinforcement Learning","created":"2023-05-23","cited_by_count":78,"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":"2102.13185","title":"Off-Policy Imitation Learning from Observations","created":"2021-02-25","cited_by_count":70,"area":"offlinerl"},{"id":"2305.13068","title":"Making Language Models Better Tool Learners with Execution Feedback","created":"2023-05-22","cited_by_count":70,"area":"agents"},{"id":"2312.11598","title":"SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution","created":"2023-12-18","cited_by_count":70,"area":"diffusion"},{"id":"2107.11003","title":"Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings","created":"2021-07-23","cited_by_count":68,"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":"2402.02420","title":"Factuality of Large Language Models: A Survey","created":"2024-02-04","cited_by_count":66,"area":null},{"id":"2212.05698","title":"MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations","created":"2022-12-12","cited_by_count":62,"area":null},{"id":"2210.08323","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","created":"2022-10-15","cited_by_count":59,"area":"offlinerl"},{"id":"2501.06994","title":"Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning","created":"2025-01-13","cited_by_count":59,"area":"offlinerl"},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58,"area":"offlinerl"},{"id":"2312.14134","title":"Diffusion Reward: Learning Rewards via Conditional Video Diffusion","created":"2023-12-21","cited_by_count":57,"area":"diffusion"},{"id":"2409.18121","title":"Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction","created":"2024-09-26","cited_by_count":54,"area":null},{"id":"2204.06601","title":"Causal Confusion and Reward Misidentification in Preference-Based Reward Learning","created":"2022-04-13","cited_by_count":53,"area":"alignment"},{"id":"2104.00053","title":"LazyDAgger: Reducing Context Switching in Interactive Imitation Learning","created":"2021-03-31","cited_by_count":51,"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":"2402.04292","title":"AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies","created":"2024-02-06","cited_by_count":50,"area":"offlinerl"},{"id":"2405.20321","title":"Vision-based Manipulation from Single Human Video with Open-World Object Graphs","created":"2024-05-30","cited_by_count":50,"area":null},{"id":"2404.19264","title":"DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets","created":"2024-04-30","cited_by_count":49,"area":null},{"id":"2503.08548","title":"TLA: Tactile-Language-Action Model for Contact-Rich Manipulation","created":"2025-03-11","cited_by_count":47,"area":"mllm"},{"id":"1910.04417","title":"Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement","created":"2019-10-10","cited_by_count":46,"area":"offlinerl"},{"id":"2207.14299","title":"Graph Inverse Reinforcement Learning from Diverse Videos","created":"2022-07-28","cited_by_count":46,"area":"offlinerl"},{"id":"2402.02330","title":"Enhance Reasoning for Large Language Models in the Game Werewolf","created":"2024-02-04","cited_by_count":46,"area":"lr"},{"id":"2206.11693","title":"Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations","created":"2022-06-23","cited_by_count":45,"area":null},{"id":"2211.12740","title":"Masked Autoencoding for Scalable and Generalizable Decision Making","created":"2022-11-23","cited_by_count":45,"area":"offlinerl"},{"id":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","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":"2202.02433","title":"Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching","created":"2022-02-04","cited_by_count":43,"area":"offlinerl"},{"id":"2105.10037","title":"Cross-domain Imitation from Observations","created":"2021-05-20","cited_by_count":42,"area":"offlinerl"},{"id":"2107.08829","title":"Visual Adversarial Imitation Learning using Variational Models","created":"2021-07-16","cited_by_count":42,"area":"offlinerl"},{"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":"2403.02709","title":"RT-Sketch: Goal-Conditioned Imitation Learning from Hand-Drawn Sketches","created":"2024-03-05","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":"2505.17006","title":"CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning","created":"2025-05-22","cited_by_count":40,"area":null},{"id":"2302.13335","title":"Diffusion Model-Augmented Behavioral Cloning","created":"2023-02-26","cited_by_count":38,"area":"diffusion"},{"id":"2204.02393","title":"Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining","created":"2022-04-05","cited_by_count":37,"area":null},{"id":"2509.04419","title":"Towards a Unified View of Large Language Model Post-Training","created":"2025-09-04","cited_by_count":36,"area":null},{"id":"2408.11537","title":"A Survey of Embodied Learning for Object-Centric Robotic Manipulation","created":"2024-08-21","cited_by_count":35,"area":null},{"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":"2111.02767","title":"RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning","created":"2021-11-04","cited_by_count":31,"area":"offlinerl"},{"id":"2309.11359","title":"Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learning","created":"2023-09-20","cited_by_count":31,"area":"offlinerl"},{"id":"2403.12203","title":"Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight","created":"2024-03-18","cited_by_count":31,"area":"deeprl"},{"id":"2506.01953","title":"Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning","created":"2025-06-02","cited_by_count":31,"area":"lr"},{"id":"2206.14349","title":"Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision","created":"2022-06-29","cited_by_count":30,"area":null},{"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":"2412.10798","title":"AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games","created":"2024-12-14","cited_by_count":28,"area":null},{"id":"2103.05910","title":"Learning from Imperfect Demonstrations from Agents with Varying Dynamics","created":"2021-03-10","cited_by_count":27,"area":"offlinerl"},{"id":"2412.06782","title":"CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction","created":"2024-12-09","cited_by_count":27,"area":null},{"id":"2206.09314","title":"Robust Imitation Learning against Variations in Environment Dynamics","created":"2022-06-19","cited_by_count":26,"area":"offlinerl"},{"id":"2405.20692","title":"In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought","created":"2024-05-31","cited_by_count":26,"area":"lr"},{"id":"2411.07223","title":"Grounding Video Models to Actions through Goal Conditioned Exploration","created":"2024-11-11","cited_by_count":26,"area":null},{"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":"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":"2202.13536","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","created":"2022-02-28","cited_by_count":23,"area":null},{"id":"2307.15690","title":"Benchmarking Offline Reinforcement Learning on Real-Robot Hardware","created":"2023-07-28","cited_by_count":23,"area":"offlinerl"},{"id":"2306.13085","title":"Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting","created":"2023-06-22","cited_by_count":22,"area":"offlinerl"},{"id":"2109.04367","title":"Multi-granularity Textual Adversarial Attack with Behavior Cloning","created":"2021-09-09","cited_by_count":21,"area":null},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21,"area":null},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"}],"next_cursor":"100"}