mlsanityData to 7 Oct 2026

Generative Adversarial Imitation Learning

arXiv 1606.03476 ↗First posted 10 Jun 2016cs.LG cs.AIcited by 1,576

Not on the map. Why?

Cited by 802 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Consider learning a policy from example expert behavior, without interaction with the expert or access to reinforcement signal. One approach is to recover the expert's cost function with inverse reinforcement learning, then extract a policy from that cost function with reinforcement learning. This approach is indirect and can be slow. We propose a new general framework for directly extracting a policy from data, as if it were obtained by reinforcement learning following inverse reinforcement learning. We show that a certain instantiation of our framework draws an analogy between imitation learning and generative adversarial networks, from which we derive a model-free imitation learning algorithm that obtains significant performance gains over existing model-free methods in imitating complex behaviors in large, high-dimensional environments.

Key facts. Cited by 1,576 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2017: 1; 2018: 28; 2019: 56; 2020: 78; 2021: 237; 2022: 237; 2023: 270; 2024: 290; 2025: 229; 2026: 150.

1,576 papers.

Sort:

By area:

  1. 2017Deep reinforcement learning from human preferencescited by 3,846
  2. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  3. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  4. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  5. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 552
  6. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
  7. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 485
  8. 2018Behavioral Cloning from Observationcited by 482
  9. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  10. 2021Implicit Behavioral Cloningcited by 442
  11. 2018Scalable agent alignment via reward modeling: a research directioncited by 438
  12. 2022Dataset Distillation by Matching Training Trajectoriescited by 437
38 more
  1. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 338
  2. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 321
  3. 2018Reward learning from human preferences and demonstrations in Ataricited by 314
  4. 2022Behavior Transformers: Cloning k modes with one stonecited by 299
  5. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 294
  6. 2019Causal Confusion in Imitation Learningcited by 286
  7. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 278
  8. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  9. 2023Imitating Human Behaviour with Diffusion Modelscited by 260
  10. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 256
  11. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 248
  12. 2023Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisonscited by 244
  13. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  14. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policiescited by 229
  15. 2021Robust Motion In-betweeningcited by 223
  16. 2026Self-Distillation Enables Continual Learningcited by 212
  17. 2020Language Conditioned Imitation Learning over Unstructured Datacited by 208
  18. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learningcited by 203
  19. 2021DexMV: Imitation Learning for Dexterous Manipulation from Human Videoscited by 194
  20. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 193
  21. 2021TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviorscited by 192
  22. 2021IQ-Learn: Inverse soft-Q Learning for Imitationcited by 191
  23. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 191
  24. 2019A Divergence Minimization Perspective on Imitation Learning Methodscited by 188
  25. 2021RvS: What is Essential for Offline RL via Supervised Learning?cited by 184
  26. 2019Imitation Learning via Off-Policy Distribution Matchingcited by 182
  27. 2022Offline Reinforcement Learning via High-Fidelity Generative Behavior Modelingcited by 177
  28. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 160
  29. 2019Goal-conditioned Imitation Learningcited by 159
  30. 2024Behavior Generation with Latent Actionscited by 159
  31. 2022The Unsurprising Effectiveness of Pre-Trained Vision Models for Controlcited by 155
  32. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  33. 2024RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedbackcited by 147
  34. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 145
  35. 2021Tianshou: a Highly Modularized Deep Reinforcement Learning Librarycited by 139
  36. 2023Vision-Language Models as Success Detectorscited by 138
  37. 2020PLAS: Latent Action Space for Offline Reinforcement Learningcited by 133
  38. 2023RoboCLIP: One Demonstration is Enough to Learn Robot Policiescited by 128

50 most cited of 1,576 All 1,576 (JSON)