mlsanityData to 7 Oct 2026

Robust Imitation of Diverse Behaviors

arXiv 1707.02747 ↗First posted 10 Jul 2017cs.LGcited by 85

Not on the map. Why?

Cited by 51 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Deep generative models have recently shown great promise in imitation learning for motor control. Given enough data, even supervised approaches can do one-shot imitation learning; however, they are vulnerable to cascading failures when the agent trajectory diverges from the demonstrations. Compared to purely supervised methods, Generative Adversarial Imitation Learning (GAIL) can learn more robust controllers from fewer demonstrations, but is inherently mode-seeking and more difficult to train. In this paper, we show how to combine the favourable aspects of these two approaches. The base of our model is a new type of variational autoencoder on demonstration trajectories that learns semantic policy embeddings. We show that these embeddings can be learned on a 9 DoF Jaco robot arm in reaching tasks, and then smoothly interpolated with a resulting smooth interpolation of reaching behavior. Leveraging these policy representations, we develop a new version of GAIL that (1) is much more robust than the purely-supervised controller, especially with few demonstrations, and (2) avoids mode collapse, capturing many diverse behaviors when GAIL on its own does not. We demonstrate our approach on learning diverse gaits from demonstration on a 2D biped and a 62 DoF 3D humanoid in the MuJoCo physics environment.

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 7; 2019: 3; 2020: 7; 2021: 16; 2022: 18; 2023: 9; 2024: 8; 2025: 10; 2026: 7.

85 papers.

Sort:

By area:

  1. 2024RT-H: Action Hierarchies Using Languagecited by 204
  2. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learningcited by 203
  3. 2020OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learningcited by 164
  4. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 124
  5. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 111
  6. 2022Adversarial Motion Priors Make Good Substitutes for Complex Reward Functionscited by 68
  7. 2021A Survey of Deep RL and IL for Autonomous Driving Policy Learningcited by 59
  8. 2021Imitation Learning: Progress, Taxonomies and Challengescited by 56
  9. 2018Multi-Agent Imitation Learning for Driving Simulationcited by 49
  10. 2022Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrationscited by 30
  11. 2022Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviorscited by 27
  12. 2022Robust Imitation Learning against Variations in Environment Dynamicscited by 26
38 more
  1. 2018Learning from Demonstration in the Wildcited by 25
  2. 2021Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systemscited by 24
  3. 2022MoCapAct: A Multi-Task Dataset for Simulated Humanoid Controlcited by 24
  4. 2018Multi-task Maximum Entropy Inverse Reinforcement Learningcited by 20
  5. 2021Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Informationcited by 18
  6. 2021AMP: Adversarial Motion Priors for Stylized Physics-Based Character Controlcited by 18
  7. 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 18
  8. 2021Collect & Infer -- a fresh look at data-efficient Reinforcement Learningcited by 17
  9. 2021Co-GAIL: Learning Diverse Strategies for Human-Robot Collaborationcited by 16
  10. 2024A Survey of Imitation Learning Methods, Environments and Metricscited by 16
  11. 2020Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learningcited by 15
  12. 2022Learning Category-Level Generalizable Object Manipulation Policy via Generative Adversarial Self-Imitation Learning from Demonstrationscited by 15
  13. 2021Imitation by Predicting Observationscited by 13
  14. 2019VILD: Variational Imitation Learning with Diverse-quality Demonstrationscited by 12
  15. 2021Inverse Contextual Bandits: Learning How Behavior Evolves over Timecited by 12
  16. 2025A Survey on Imitation Learning for Contact-Rich Tasks in Roboticscited by 12
  17. 2020Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Netscited by 11
  18. 2021Adversarial Imitation Learning with Trajectorial Augmentation and Correctioncited by 11
  19. 2022Imitation Learning from Observations under Transition Model Disparitycited by 11
  20. 2018Maximum Causal Tsallis Entropy Imitation Learningcited by 10
  21. 2020Episodic Self-Imitation Learning with Hindsightcited by 10
  22. 2021Deep reinforcement learning for guidewire navigation in coronary artery phantomcited by 9
  23. 2018LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrationscited by 8
  24. 2023Inverse Reinforcement Learning with the Average Reward Criterioncited by 8
  25. 2023Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertaintycited by 8
  26. 2022Robust Imitation of a Few Demonstrations with a Backwards Modelcited by 7
  27. 2022Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferencescited by 7
  28. 2025Subtask-Aware Visual Reward Learning from Segmented Demonstrationscited by 7
  29. 2021Grounded Relational Inference: Domain Knowledge Driven Explainable Autonomous Drivingcited by 6
  30. 2022ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characterscited by 6
  31. 2024MAPLE: A Framework for Active Preference Learning Guided by Large Language Modelscited by 6
  32. 2024Consistency Matters: Defining Demonstration Data Quality Metrics in Robot Learning from Demonstrationcited by 6
  33. 2025MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policiescited by 6
  34. 2021No Need for Interactions: Robust Model-Based Imitation Learning using Neural ODEcited by 5
  35. 2022Diverse Imitation Learning via Self-Organizing Generative Modelscited by 5
  36. 2022On Efficient Online Imitation Learning via Classificationcited by 5
  37. 2022Robust Imitation via Mirror Descent Inverse Reinforcement Learningcited by 5
  38. 2024Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learningcited by 4

50 most cited of 85 All 85 (JSON)