mlsanityData to 7 Oct 2026

Imitation learning methods

746 papers1 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: imitation, imitation learning, expert, demonstrations, policy

Key facts. Imitation learning methods: 746 papers on arXiv since 2018 (data through 7 Oct 2026). 101 of its 746 mapped papers (14%) cite “An Algorithmic Perspective on Imitation Learning” (2018, arXiv 1811.06711). 97 of its 746 mapped papers (13%) cite “Behavioral Cloning from Observation” (2018, arXiv 1805.01954). 8 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

8 new papers, 17 Sep – 7 Oct; 1 this week.

  1. This week · 1
  2. Interleaved Projected Gradient Descent for Safe Imitation Learning
  3. Earlier · 7
  4. Reward-DAgger: Robot-Gated Interactive Imitation Learning with General-Purpose Progress-Based Reward Models also fits: Language-conditioned policies and VLAs
  5. Measuring the Stability Assumption Behind Action Chunking also fits: Language-conditioned policies and VLAs
  6. Disagreement-Regularized Imitation Learning for Image-Based Continuous Control with Gaussian and Beta Policies
  7. Provable Benefits of Regularization: Fast Rates for Adversarial Imitation Learning
  8. Beyond Conservatism: Recoverability-Conditioned Exploration for Model-Based Imitation Learning
  9. The Statistical Benefits of Multiple Responses for Learning from Demonstrations also fits: Inverse reinforcement learning
  10. Policy-Calibrated DAgger: Offline Calibrated Noise Injection for Imitation Learning also fits: Robot manipulation imitation learning

Foundations

Most cited by papers here

  1. An Algorithmic Perspective on Imitation Learning2018cited by 101 here
  2. Behavioral Cloning from Observation2018cited by 97 here
  3. Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning2018cited by 96 here
  4. SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards2019cited by 72 here
  5. A Divergence Minimization Perspective on Imitation Learning Methods2019cited by 68 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2018Behavioral Cloning from Observationcited by 97 here
  2. 2019Provably Efficient Imitation Learning from Observation Alonecited by 42 here
  3. 2019Imitation Learning as f-Divergence Minimizationcited by 54 here
  4. 2019A Divergence Minimization Perspective on Imitation Learning Methodscited by 68 here
  5. 2020Primal Wasserstein Imitation Learningcited by 51 here
19 more it builds on, not in this chain
  1. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 34 here
  2. 2018Generative Adversarial Imitation from Observationcited by 56 here
  3. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learningcited by 96 here
  4. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 28 here
  5. 2018An Algorithmic Perspective on Imitation Learningcited by 101 here
  6. 2019Imitation Learning from Imperfect Demonstrationcited by 45 here
  7. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 45 here
  8. 2019SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewardscited by 72 here
  9. 2019Causal Confusion in Imitation Learningcited by 37 here
  10. 2019Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrationscited by 29 here
  11. 2019Imitation Learning via Off-Policy Distribution Matchingcited by 68 here
  12. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 49 here
  13. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 35 here
  14. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 35 here
  15. 2020Toward the Fundamental Limits of Imitation Learningcited by 36 here
  16. 2021Off-Policy Imitation Learning from Observationscited by 34 here
  17. 2021Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gapcited by 32 here
  18. 2021IQ-Learn: Inverse soft-Q Learning for Imitationcited by 59 here
  19. 2022Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrationscited by 29 here

The 24 most cited of 852.

Browse

30 of 746, ranked 6–35

  1. 6Imitation Learning via Off-Policy Distribution Matching201968
  2. 7IQ-Learn: Inverse soft-Q Learning for Imitation202159
  3. 8Generative Adversarial Imitation from Observation201856
  4. 9Imitation Learning as f-Divergence Minimization201954
  5. 10Primal Wasserstein Imitation Learning202051
  6. 11Imitation Learning from Imperfect Demonstration201945
  7. 12Provably Efficient Imitation Learning from Observation Alone201942
  8. 13Causal Confusion in Imitation Learning201937
  9. 14Toward the Fundamental Limits of Imitation Learning202036
  10. 15Off-Policy Imitation Learning from Observations202134
All 30
  1. 16Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap202132
  2. 17Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations202229
  3. 18Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations201929
  4. 19Error Bounds of Imitating Policies and Environments202028
  5. 20Recent Advances in Imitation Learning from Observation201928
  6. 21HG-DAgger: Interactive Imitation Learning with Human Experts201828
  7. 22Implicit Behavioral Cloning202127
  8. 23Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation201927
  9. 24Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow201827
  10. 25What Matters for Adversarial Imitation Learning?202126
  11. 26Imitating Latent Policies from Observation201825
  12. 27Multi-Agent Generative Adversarial Imitation Learning201823
  13. 28Feedback in Imitation Learning: The Three Regimes of Covariate Shift202122
  14. 29Wasserstein Adversarial Imitation Learning201922
  15. 30State Alignment-based Imitation Learning201922
  16. 31EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning201822
  17. 32Sample-Efficient Imitation Learning via Generative Adversarial Nets201822
  18. 33Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning202420
  19. 34MobILE: Model-Based Imitation Learning From Observation Alone202120
  20. 35Offline Learning from Demonstrations and Unlabeled Experience202020