mlsanityData to 14 Oct 2026

Behavioral Cloning from Observation

arXiv 1805.01954 ↗First posted 4 May 2018cs.AIcited by 492

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Humans often learn how to perform tasks via imitation: they observe others perform a task, and then very quickly infer the appropriate actions to take based on their observations. While extending this paradigm to autonomous agents is a well-studied problem in general, there are two particular aspects that have largely been overlooked: (1) that the learning is done from observation only (i.e., without explicit action information), and (2) that the learning is typically done very quickly. In this work, we propose a two-phase, autonomous imitation learning technique called behavioral cloning from observation (BCO), that aims to provide improved performance with respect to both of these aspects. First, we allow the agent to acquire experience in a self-supervised fashion. This experience is used to develop a model which is then utilized to learn a particular task by observing an expert perform that task without the knowledge of the specific actions taken. We experimentally compare BCO to imitation learning methods, including the state-of-the-art, generative adversarial imitation learning (GAIL) technique, and we show comparable task performance in several different simulation domains while exhibiting increased learning speed after expert trajectories become available.

Key facts. Cited by 492 papers in the map (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 11 of its 31 references that are in the map. First posted on arXiv 4 May 2018.

Builds on

11 of 31 references.

References · 11

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Trust Region Policy Optimizationcited by 2,580
  3. 2016OpenAI Gymcited by 1,736
  4. 2016Generative Adversarial Imitation Learningcited by 1,597
  5. 2016End to End Learning for Self-Driving Carscited by 1,009
  6. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 406
  7. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  8. 2017Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learningcited by 85
  9. 2016Model-Free Imitation Learning with Policy Optimizationcited by 52
  10. 2017Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learningcited by 27
  11. 2016Learning Transferable Policies for Monocular Reactive MAV Controlcited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 13; 2020: 17; 2021: 42; 2022: 68; 2023: 83; 2024: 90; 2025: 98; 2026: 80.

492 papers.

Sort:

By area:

  1. 2024Genie: Generative Interactive Environmentscited by 747
  2. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  3. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 478
  4. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 345
  5. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 327
  6. 2022Behavior Transformers: Cloning k modes with one stonecited by 304
  7. 2023Tool Learning with Foundation Modelscited by 302
  8. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 260
  9. 2022Pre-Trained Language Models for Interactive Decision-Makingcited by 221
  10. 2023Any-point Trajectory Modeling for Policy Learningcited by 215
  11. 2021DexMV: Imitation Learning for Dexterous Manipulation from Human Videoscited by 206
  12. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 181
38 more
  1. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Taskscited by 168
  2. 2023Learning to Act from Actionless Videos through Dense Correspondencescited by 164
  3. 2021The Surprising Effectiveness of Representation Learning for Visual Imitationcited by 154
  4. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 148
  5. 2023Getting aligned on representational alignmentcited by 143
  6. 2023HIQL: Offline Goal-Conditioned RL with Latent States as Actionscited by 141
  7. 2023MiniLLM: On-Policy Distillation of Large Language Modelscited by 139
  8. 2019Imitation Learning as f-Divergence Minimizationcited by 123
  9. 2020Primal Wasserstein Imitation Learningcited by 121
  10. 2023Learning to Act without Actionscited by 121
  11. 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learningcited by 108
  12. 2021XIRL: Cross-embodiment Inverse Reinforcement Learningcited by 107
  13. 2023UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learningcited by 107
  14. 2023Motif: Intrinsic Motivation from Artificial Intelligence Feedbackcited by 102
  15. 2020Toward the Fundamental Limits of Imitation Learningcited by 96
  16. 2022Instruction-driven history-aware policies for robotic manipulationscited by 94
  17. 2019Recent Advances in Imitation Learning from Observationcited by 93
  18. 2024SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agentscited by 93
  19. 2020State-Only Imitation Learning for Dexterous Manipulationcited by 91
  20. 2021Learning by Watching: Physical Imitation of Manipulation Skills from Human Videoscited by 87
  21. 2021S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learningcited by 85
  22. 2023Optimizing DDPM Sampling with Shortcut Fine-Tuningcited by 81
  23. 2019Provably Efficient Imitation Learning from Observation Alonecited by 78
  24. 2023Video Prediction Models as Rewards for Reinforcement Learningcited by 78
  25. 2023Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrationscited by 75
  26. 2019State Alignment-based Imitation Learningcited by 73
  27. 2020Safe Imitation Learning via Fast Bayesian Reward Inference from Preferencescited by 73
  28. 2021Off-Policy Imitation Learning from Observationscited by 70
  29. 2023Making Language Models Better Tool Learners with Execution Feedbackcited by 70
  30. 2023SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Executioncited by 70
  31. 2021Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settingscited by 68
  32. 2023Reinforcement Learning from Passive Data via Latent Intentionscited by 68
  33. 2024Factuality of Large Language Models: A Surveycited by 66
  34. 2022MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrationscited by 62
  35. 2022A Policy-Guided Imitation Approach for Offline Reinforcement Learningcited by 59
  36. 2025Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learningcited by 59
  37. 2021Imitation Learning: Progress, Taxonomies and Challengescited by 58
  38. 2023Diffusion Reward: Learning Rewards via Conditional Video Diffusioncited by 57

50 most cited of 492 All 492 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2020Imitating Unknown Policies via Exploration
  2. 2020Fighting Copycat Agents in Behavioral Cloning from Observation Histories
  3. 2018Generative Adversarial Imitation from Observation
  4. 2022Diverse Imitation Learning via Self-Organizing Generative Models
  5. 2024Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
  6. 2022ABC: Adversarial Behavioral Cloning for Offline Mode-Seeking Imitation Learning
  7. 2025A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search
  8. 2022Model-based Offline Imitation Learning with Non-expert Data