mlsanityData to 7 Oct 2026

A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges

arXiv 2309.02473 ↗First posted 5 Sep 2023cs.LG cs.AI cs.ROcited by 145

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

Abstract (arXiv)

In recent years, the development of robotics and artificial intelligence (AI) systems has been nothing short of remarkable. As these systems continue to evolve, they are being utilized in increasingly complex and unstructured environments, such as autonomous driving, aerial robotics, and natural language processing. As a consequence, programming their behaviors manually or defining their behavior through reward functions (as done in reinforcement learning (RL)) has become exceedingly difficult. This is because such environments require a high degree of flexibility and adaptability, making it challenging to specify an optimal set of rules or reward signals that can account for all possible situations. In such environments, learning from an expert's behavior through imitation is often more appealing. This is where imitation learning (IL) comes into play - a process where desired behavior is learned by imitating an expert's behavior, which is provided through demonstrations. This paper aims to provide an introduction to IL and an overview of its underlying assumptions and approaches. It also offers a detailed description of recent advances and emerging areas of research in the field. Additionally, the paper discusses how researchers have addressed common challenges associated with IL and provides potential directions for future research. Overall, the goal of the paper is to provide a comprehensive guide to the growing field of IL in robotics and AI.

Key facts. Cited by 145 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 64 of its 127 references that are in the map. First posted on arXiv 5 Sep 2023.

Builds on

64 of 127 references.

Closest ancestors · 31

Same direction, newest first

  1. 2023CEIL: Generalized Contextual Imitation Learning26 Jun
  2. 2023Active Policy Improvement from Multiple Black-box Oracles17 Jun
  3. 2023MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations30 Mar
  4. 2022Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction20 Jul
  5. 2022Discriminator-Guided Model-Based Offline Imitation Learning1 Jul
  6. 2022Watch and Match: Supercharging Imitation with Regularized Optimal Transport30 Jun
  7. 2022Robust Imitation Learning against Variations in Environment Dynamics19 Jun
  8. 2022ARC - Actor Residual Critic for Adversarial Imitation Learning5 Jun
  9. 2022Imitation Learning from Observations under Transition Model Disparity25 Apr
  10. 2022Imitation Learning by Estimating Expertise of Demonstrators2 Feb
  11. 2021TRAIL: Near-Optimal Imitation Learning with Suboptimal Data27 Oct
  12. 2021Cross-Domain Imitation Learning via Optimal Transport7 Oct
19 more
  1. 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning17 Sep
  2. 2021Implicit Behavioral Cloning1 Sep
  3. 2021Imitation by Predicting Observations8 Jul
  4. 2021What Matters for Adversarial Imitation Learning?1 Jun
  5. 2021Cross-domain Imitation from Observations20 May
  6. 2020Fighting Copycat Agents in Behavioral Cloning from Observation Histories28 Oct
  7. 2020Primal Wasserstein Imitation Learning8 Jun
  8. 2020Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences21 Feb
  9. 2019Recent Advances in Imitation Learning from Observation30 May
  10. 2019Causal Confusion in Imitation Learning28 May
  11. 2019Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation16 May
  12. 2019Imitation Learning from Imperfect Demonstration27 Jan
  13. 2018An Algorithmic Perspective on Imitation Learning16 Nov
  14. 2018HG-DAgger: Interactive Imitation Learning with Human Experts5 Oct
  15. 2018Multi-Agent Generative Adversarial Imitation Learning26 Jul
  16. 2018EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning22 Jul
  17. 2018Generative Adversarial Imitation from Observation17 Jul
  18. 2018Imitating Latent Policies from Observation21 May
  19. 2018Behavioral Cloning from Observation4 May

Other references · 33

  1. 2016Generative Adversarial Imitation Learningcited by 1,576
  2. 2021Domain Generalization: A Surveycited by 760
  3. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  4. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  5. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
  6. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
  7. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 391
  8. 2016Cooperative Inverse Reinforcement Learningcited by 298
  9. 2021How to Train Your Energy-Based Modelscited by 271
  10. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 256
  11. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Playcited by 214
  12. 2015Maximum Entropy Deep Inverse Reinforcement Learningcited by 173
21 more
  1. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  2. 2018Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applicationscited by 122
  3. 2021OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimationcited by 121
  4. 2022Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scalecited by 116
  5. 2017Third-Person Imitation Learningcited by 103
  6. 2020Human-in-the-Loop Imitation Learning using Remote Teleoperationcited by 103
  7. 2021XIRL: Cross-embodiment Inverse Reinforcement Learningcited by 101
  8. 2018Playing hard exploration games by watching YouTubecited by 98
  9. 2017Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Predictioncited by 93
  10. 2019A Survey of Optimization Methods from a Machine Learning Perspectivecited by 90
  11. 2023Data Quality in Imitation Learningcited by 72
  12. 2021Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulationcited by 59
  13. 2023Waypoint-Based Imitation Learning for Robotic Manipulationcited by 59
  14. 2021Scalable Bayesian Inverse Reinforcement Learningcited by 56
  15. 2023HYDRA: Hybrid Robot Actions for Imitation Learningcited by 54
  16. 2016Model-Free Imitation Learning with Policy Optimizationcited by 52
  17. 2021LazyDAgger: Reducing Context Switching in Interactive Imitation Learningcited by 50
  18. 2022Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimizationcited by 44
  19. 2020Modeling Human Driving Behavior through Generative Adversarial Imitation Learningcited by 43
  20. 2022Active Exploration for Inverse Reinforcement Learningcited by 27
  21. 2022SelfD: Self-Learning Large-Scale Driving Policies From the Webcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 28; 2025: 72; 2026: 41.

145 papers.

Sort:

By area:

  1. 2024RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulationcited by 166
  2. 2025Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Modelscited by 77
  3. 2025Diffusion Models for Robotic Manipulation: A Surveycited by 39
  4. 2025Multi-agent Embodied AI: Advances and Future Directionscited by 36
  5. 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulationcited by 34
  6. 2025EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modelingcited by 29
  7. 2025Learning Long-Context Diffusion Policies via Past-Token Predictioncited by 28
  8. 2025SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modelingcited by 27
  9. 2024Autoregressive Action Sequence Learning for Robotic Manipulationcited by 26
  10. 2025SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulationcited by 21
  11. 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agentscited by 19
  12. 2024MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulationcited by 18
38 more
  1. 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 18
  2. 2024Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomycited by 16
  3. 2025CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-Worldcited by 16
  4. 2025Curating Demonstrations using Online Experiencecited by 16
  5. 2024Learning Useful Representations of Recurrent Neural Network Weight Matricescited by 13
  6. 2024SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systemscited by 13
  7. 2025Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Modelscited by 13
  8. 2023When Meta-Learning Meets Online and Continual Learning: A Surveycited by 12
  9. 2024EgoNav: Egocentric Scene-aware Human Trajectory Predictioncited by 9
  10. 2024Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitatorscited by 9
  11. 2023Learning Human-like Representations to Enable Learning Human Valuescited by 7
  12. 2024Autonomous Driving at Unsignalized Intersections: A Review of Decision-Making Challenges and Reinforcement Learning-Based Solutionscited by 7
  13. 2025Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithmscited by 7
  14. 2025Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chesscited by 7
  15. 2026VLA Knows Its Limits: Adaptive Execution Horizons for Robot Policiescited by 7
  16. 2024KOI: Accelerating Online Imitation Learning via Hybrid Key-state Guidancecited by 6
  17. 2025Dynamic Rank Adjustment in Diffusion Policies for Efficient and Flexible Trainingcited by 6
  18. 2025TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Controlcited by 6
  19. 2025Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanismcited by 6
  20. 2025ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL Problemscited by 6
  21. 2024MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learningcited by 5
  22. 2025Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformerscited by 5
  23. 2025Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulationcited by 5
  24. 2025Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learningcited by 5
  25. 2025Human-in-the-loop Online Rejection Sampling for Robotic Manipulationcited by 5
  26. 2024Walking the Values in Bayesian Inverse Reinforcement Learningcited by 4
  27. 2024Diversifying Policy Behaviors with Extrinsic Behavioral Curiositycited by 4
  28. 2024Proleptic Temporal Ensemble for Improving the Speed of Robot Tasks Generated by Imitation Learningcited by 4
  29. 2024Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Explorationcited by 4
  30. 2024Sample-efficient Unsupervised Policy Cloning from Ensemble Self-supervised Labeled Videoscited by 4
  31. 2025Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learningcited by 4
  32. 2025PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulationcited by 4
  33. 2025Improving Generalization Ability of Robotic Imitation Learning by Resolving Causal Confusion in Observationscited by 4
  34. 2025Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representationscited by 4
  35. 2023Leveraging Optimal Transport for Enhanced Offline Reinforcement Learning in Surgical Robotic Environmentscited by 3
  36. 2024BeTAIL: Behavior Transformer Adversarial Imitation Learning from Human Racing Gameplaycited by 3
  37. 2024A survey of air combat behavior modeling using machine learningcited by 3
  38. 2024CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interactioncited by 3

50 most cited of 145 All 145 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2021Imitation Learning: Progress, Taxonomies and Challenges
  2. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
  3. 2024A Survey of Imitation Learning Methods, Environments and Metrics
  4. 2022Interactive Imitation Learning in Robotics: A Survey
  5. 2025Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challenges
  6. 2021Imitation Learning by Reinforcement Learning
  7. 2025An Introduction to Deep Reinforcement and Imitation Learning
  8. 2024Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning