mlsanityData to 14 Oct 2026

An Algorithmic Perspective on Imitation Learning

arXiv 1811.06711 ↗First posted 16 Nov 2018cs.RO cs.LGcited by 459

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

Abstract (arXiv)

As robots and other intelligent agents move from simple environments and problems to more complex, unstructured settings, manually programming their behavior has become increasingly challenging and expensive. Often, it is easier for a teacher to demonstrate a desired behavior rather than attempt to manually engineer it. This process of learning from demonstrations, and the study of algorithms to do so, is called imitation learning. This work provides an introduction to imitation learning. It covers the underlying assumptions, approaches, and how they relate; the rich set of algorithms developed to tackle the problem; and advice on effective tools and implementation. We intend this paper to serve two audiences. First, we want to familiarize machine learning experts with the challenges of imitation learning, particularly those arising in robotics, and the interesting theoretical and practical distinctions between it and more familiar frameworks like statistical supervised learning theory and reinforcement learning. Second, we want to give roboticists and experts in applied artificial intelligence a broader appreciation for the frameworks and tools available for imitation learning.

Key facts. Cited by 459 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 33 of its 236 references that are in the map. First posted on arXiv 16 Nov 2018.

Builds on

33 of 236 references.

References · 33

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2015Trust Region Policy Optimizationcited by 2,580
  3. 2016Generative Adversarial Imitation Learningcited by 1,597
  4. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 968
  5. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  6. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 669
  7. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
  8. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 406
  9. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  10. 2016Cooperative Inverse Reinforcement Learningcited by 300
  11. 2017One-Shot Imitation Learningcited by 233
  12. 2017One-Shot Visual Imitation Learning via Meta-Learningcited by 228
21 more
  1. 2015Action-Conditional Video Prediction using Deep Networks in Atari Gamescited by 172
  2. 2016A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Modelscited by 168
  3. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  4. 2015Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systemscited by 134
  5. 2014Reinforcement and Imitation Learning via Interactive No-Regret Learningcited by 118
  6. 2017Third-Person Imitation Learningcited by 103
  7. 2017Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstrationcited by 100
  8. 2015Gaussian Processes for Data-Efficient Learning in Robotics and Controlcited by 98
  9. 2017Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Predictioncited by 93
  10. 2017Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulationcited by 90
  11. 2017Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learningcited by 85
  12. 2016Unsupervised Perceptual Rewards for Imitation Learningcited by 65
  13. 2016Model-Free Imitation Learning with Policy Optimizationcited by 52
  14. 2015Learning to Search Better Than Your Teachercited by 50
  15. 2017OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learningcited by 40
  16. 2016Learning Preferences for Manipulation Tasks from Online Coactive Feedbackcited by 31
  17. 2014Interactive Policy Learning through Confidence-Based Autonomycited by 29
  18. 2013Computational Rationalization: The Inverse Equilibrium Problemcited by 24
  19. 2013Model-Based Bayesian Explorationcited by 21
  20. 2016HIRL: Hierarchical Inverse Reinforcement Learning for Long-Horizon Tasks with Delayed Rewardscited by 15
  21. 2014Conditional Density Estimation with Dimensionality Reduction via Squared-Loss Conditional Entropy Minimizationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 13; 2020: 21; 2021: 62; 2022: 77; 2023: 75; 2024: 65; 2025: 87; 2026: 58.

459 papers.

Sort:

By area:

  1. 2021Implicit Behavioral Cloningcited by 452
  2. 2022Dataset Distillation by Matching Training Trajectoriescited by 442
  3. 2022Behavior Transformers: Cloning k modes with one stonecited by 304
  4. 2024Diffusion Policy Policy Optimizationcited by 280
  5. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 260
  6. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policiescited by 236
  7. 2022Interactive Language: Talking to Robots in Real Timecited by 218
  8. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Drivingcited by 198
  9. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  10. 2023Learning to Act from Actionless Videos through Dense Correspondencescited by 164
  11. 2023Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Modelscited by 161
  12. 2024Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learningcited by 155
38 more
  1. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 148
  2. 2019Imitation Learning as f-Divergence Minimizationcited by 123
  3. 2023Policy Representation via Diffusion Probability Model for Reinforcement Learningcited by 112
  4. 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learningcited by 108
  5. 2021XIRL: Cross-embodiment Inverse Reinforcement Learningcited by 107
  6. 2019Recent Advances in Imitation Learning from Observationcited by 93
  7. 2022Differentiable Raycasting for Self-supervised Occupancy Forecastingcited by 84
  8. 2022Tutorial on amortized optimizationcited by 83
  9. 2022You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstrationcited by 81
  10. 2022Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximationcited by 81
  11. 2021Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Taskscited by 78
  12. 2021A Survey on Interpretable Reinforcement Learningcited by 73
  13. 2020Offline Learning from Demonstrations and Unlabeled Experiencecited by 72
  14. 2020Fighting Copycat Agents in Behavioral Cloning from Observation Historiescited by 71
  15. 2024Preserving Diversity in Supervised Fine-Tuning of Large Language Modelscited by 70
  16. 2022See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulationcited by 68
  17. 2024DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agentscited by 68
  18. 2024Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matchingcited by 65
  19. 2023Grounding 3D Object Affordance from 2D Interactions in Imagescited by 62
  20. 2021A Survey of Deep RL and IL for Autonomous Driving Policy Learningcited by 61
  21. 2021GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Drivingcited by 60
  22. 2022Adversarial Training for High-Stakes Reliabilitycited by 60
  23. 2021Imitation Learning: Progress, Taxonomies and Challengescited by 58
  24. 2023Benchmarks and Algorithms for Offline Preference-Based Reward Learningcited by 56
  25. 2022Motion Policy Networkscited by 55
  26. 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrationscited by 53
  27. 2020Model-Based Inverse Reinforcement Learning from Visual Demonstrationscited by 52
  28. 2021LazyDAgger: Reducing Context Switching in Interactive Imitation Learningcited by 51
  29. 2020Deep Imitation Learning for Bimanual Robotic Manipulationcited by 50
  30. 2024AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policiescited by 50
  31. 2022Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimizationcited by 49
  32. 2023EDMP: Ensemble-of-costs-guided Diffusion for Motion Planningcited by 49
  33. 2025Leave No Observation Behind: Real-time Correction for VLA Action Chunkscited by 46
  34. 2026World Model for Robot Learning: A Comprehensive Surveycited by 46
  35. 2023A Survey on Causal Reinforcement Learningcited by 45
  36. 2023SMART: Self-supervised Multi-task pretrAining with contRol Transformerscited by 44
  37. 2022PseudoClick: Interactive Image Segmentation with Click Imitationcited by 42
  38. 2022Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guaranteescited by 42

50 most cited of 459 All 459 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
  2. 2025Robot Learning: A Tutorial
  3. 2025Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challenges
  4. 2022Imitation Learning by Estimating Expertise of Demonstrators
  5. 2024A Survey of Imitation Learning Methods, Environments and Metrics
  6. 2021Learning from Imperfect Demonstrations from Agents with Varying Dynamics
  7. 2020Scalable Multi-Task Imitation Learning with Autonomous Improvement
  8. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations