mlsanityData to 7 Oct 2026

Diverse Imitation Learning via Self-Organizing Generative Models

arXiv 2205.03484 ↗First posted 6 May 2022cs.LGcited by 5

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

Abstract (arXiv)

Imitation learning is the task of replicating expert policy from demonstrations, without access to a reward function. This task becomes particularly challenging when the expert exhibits a mixture of behaviors. Prior work has introduced latent variables to model variations of the expert policy. However, our experiments show that the existing works do not exhibit appropriate imitation of individual modes. To tackle this problem, we adopt an encoder-free generative model for behavior cloning (BC) to accurately distinguish and imitate different modes. Then, we integrate it with GAIL to make the learning robust towards compounding errors at unseen states. We show that our method significantly outperforms the state of the art across multiple experiments.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 20 of its 61 references that are in the map. First posted on arXiv 6 May 2022.

Builds on

20 of 61 references.

Closest ancestors · 2

Same direction, newest first

  1. 2021Imitation Learning: Progress, Taxonomies and Challenges23 Jun
  2. 2020Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets19 May

Other references · 18

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2015Continuous control with deep reinforcement learningcited by 3,279
  4. 2015Trust Region Policy Optimizationcited by 2,503
  5. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  6. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  7. 2016Generative Adversarial Imitation Learningcited by 1,576
  8. 2017Hindsight Experience Replaycited by 1,096
  9. 2017A Brief Survey of Deep Reinforcement Learningcited by 466
  10. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
  11. 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 256
  12. 2017Optimizing the Latent Space of Generative Networkscited by 157
6 more
  1. 2017Robust Imitation of Diverse Behaviorscited by 85
  2. 2020Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errorscited by 80
  3. 2017Learning human behaviors from motion capture by adversarial imitationcited by 75
  4. 2017Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Netscited by 64
  5. 2021Efficient Deep Reinforcement Learning with Imitative Expert Priors for Autonomous Drivingcited by 46
  6. 2018Non-Adversarial Image Synthesis with Generative Latent Nearest Neighborscited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 18
  2. 2025ADPro: a Test-time Adaptive Diffusion Policy via Manifold-constrained Denoising and Task-aware Initialization for Robotic Manipulationcited by 4
  3. 2026Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generationcited by 3
  4. 2025Restoring Noisy Demonstration for Imitation Learning With Diffusion Modelscited by 1
  5. 2026Expert Behavior Prior Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior
  2. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
  3. 2020Imitating Unknown Policies via Exploration
  4. 2019Generative predecessor models for sample-efficient imitation learning
  5. 2021Imitation by Predicting Observations
  6. 2019Imitation Learning as f-Divergence Minimization
  7. 2018Behavioral Cloning from Observation
  8. 2026Difference-Aware Retrieval Policies for Imitation Learning