mlsanityData to 14 Oct 2026

Imitation Learning: Progress, Taxonomies and Challenges

arXiv 2106.12177 ↗First posted 23 Jun 2021cs.LG cs.ROcited by 58

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

Abstract (arXiv)

Imitation learning aims to extract knowledge from human experts' demonstrations or artificially created agents in order to replicate their behaviors. Its success has been demonstrated in areas such as video games, autonomous driving, robotic simulations and object manipulation. However, this replicating process could be problematic, such as the performance is highly dependent on the demonstration quality, and most trained agents are limited to perform well in task-specific environments. In this survey, we provide a systematic review on imitation learning. We first introduce the background knowledge from development history and preliminaries, followed by presenting different taxonomies within Imitation Learning and key milestones of the field. We then detail challenges in learning strategies and present research opportunities with learning policy from suboptimal demonstration, voice instructions and other associated optimization schemes.

Key facts. Cited by 58 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 69 of its 123 references that are in the map. First posted on arXiv 23 Jun 2021.

Builds on

69 of 123 references.

Closest ancestors · 20

Same direction, newest first

  1. 2021Off-Policy Imitation Learning from Observations25 Feb
  2. 2021On the Sample Complexity of Stability Constrained Imitation Learning18 Feb
  3. 2021Robust Maximum Entropy Behavior Cloning4 Jan
  4. 2020Non-Adversarial Imitation Learning and its Connections to Adversarial Methods8 Aug
  5. 2020Intrinsic Reward Driven Imitation Learning via Generative Model26 Jun
  6. 2020Benchmarking End-to-End Behavioural Cloning on Video Games2 Apr
  7. 2020Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences21 Feb
  8. 2019Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Model3 Jul
  9. 2019Goal-conditioned Imitation Learning13 Jun
  10. 2019Recent Advances in Imitation Learning from Observation30 May
  11. 2019Causal Confusion in Imitation Learning28 May
  12. 2019Provably Efficient Imitation Learning from Observation Alone27 May
8 more
  1. 2019Imitation Learning from Video by Leveraging Proprioception22 May
  2. 2018An Algorithmic Perspective on Imitation Learning16 Nov
  3. 2018Multi-Agent Generative Adversarial Imitation Learning26 Jul
  4. 2018Generative Adversarial Imitation from Observation17 Jul
  5. 2018Self-Imitation Learning14 Jun
  6. 2018Imitating Latent Policies from Observation21 May
  7. 2018Learning Temporal Strategic Relationships using Generative Adversarial Imitation Learning13 May
  8. 2018Behavioral Cloning from Observation4 May

Other references · 49

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2015Trust Region Policy Optimizationcited by 2,580
  4. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  5. 2016Generative Adversarial Imitation Learningcited by 1,597
  6. 2017Hindsight Experience Replaycited by 1,136
  7. 2017End-to-end Driving via Conditional Imitation Learningcited by 485
  8. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 459
  9. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 406
  10. 2019Learning by Cheatingcited by 383
  11. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 346
  12. 2017Overcoming Exploration in Reinforcement Learning with Demonstrationscited by 340
37 more
  1. 2018Reward learning from human preferences and demonstrations in Ataricited by 316
  2. 2019Learning Latent Plans from Playcited by 316
  3. 2018Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigationcited by 305
  4. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 298
  5. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 289
  6. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 260
  7. 2017One-Shot Imitation Learningcited by 233
  8. 2019MineRL: A Large-Scale Dataset of Minecraft Demonstrationscited by 215
  9. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  10. 2018One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learningcited by 148
  11. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 126
  12. 2020Reward-rational (implicit) choice: A unifying formalism for reward learningcited by 120
  13. 2014Reinforcement and Imitation Learning via Interactive No-Regret Learningcited by 118
  14. 2018Zero-Shot Visual Imitationcited by 117
  15. 2017Third-Person Imitation Learningcited by 103
  16. 2018Playing hard exploration games by watching YouTubecited by 99
  17. 2017Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Predictioncited by 93
  18. 2017Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulationcited by 90
  19. 2017Robust Imitation of Diverse Behaviorscited by 86
  20. 2018Learning Montezuma's Revenge from a Single Demonstrationcited by 80
  21. 2019Learning Reward Functions by Integrating Human Demonstrations and Preferencescited by 64
  22. 2019Deep Reinforcement Learning from Policy-Dependent Human Feedbackcited by 56
  23. 2020Model-Based Inverse Reinforcement Learning from Visual Demonstrationscited by 52
  24. 2021LazyDAgger: Reducing Context Switching in Interactive Imitation Learningcited by 51
  25. 2015Learning to Search Better Than Your Teachercited by 50
  26. 2018Multi-Agent Imitation Learning for Driving Simulationcited by 50
  27. 2018Generating Multi-Agent Trajectories using Programmatic Weak Supervisioncited by 46
  28. 2017Data-driven Planning via Imitation Learningcited by 36
  29. 2021Self-Imitation Learning by Planningcited by 26
  30. 2020An Imitation Learning Approach for Cache Replacementcited by 24
  31. 2021Imitation Learning for Variable Speed Contact Motion for Operation up to Control Bandwidthcited by 16
  32. 2020Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraftcited by 15
  33. 2019Optimal Passenger-Seeking Policies on E-hailing Platforms Using Markov Decision Process and Imitation Learningcited by 10
  34. 2020Motion2Vec: Semi-Supervised Representation Learning from Surgical Videoscited by 10
  35. 2020Driving Through Ghosts: Behavioral Cloning with False Positivescited by 8
  36. 2018Imitation Learning for End to End Vehicle Longitudinal Control with Forward Cameracited by 5
  37. 2019Inverse Reinforcement Learning with Multiple Ranked Expertscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 11; 2024: 24; 2025: 14; 2026: 7.

58 papers.

Sort:

By area:

  1. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  2. 2023Coherent Soft Imitation Learningcited by 22
  3. 2024Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy Diffusioncited by 21
  4. 2024Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedbackcited by 11
  5. 2024QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learningcited by 10
  6. 2022Diverse Imitation Learning via Self-Organizing Generative Modelscited by 5
  7. 2024HANDI: Hand-Centric Text-and-Image Conditioned Video Generationcited by 5
  8. 2025A Knowledge-Driven Diffusion Policy for End-to-End Autonomous Driving Based on Expert Routingcited by 5
  9. 2025Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learningcited by 4
  10. 2023Unlabeled Imperfect Demonstrations in Adversarial Imitation Learningcited by 3
  11. 2023Programmatic Imitation Learning from Unlabeled and Noisy Demonstrationscited by 3
  12. 2024Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarkingcited by 3
38 more
  1. 2024Combining RL and IL using a dynamic, performance-based modulation over learning signals and its application to local planningcited by 3
  2. 2024Online Adaptation for Enhancing Imitation Learning Policiescited by 3
  3. 2024Social Learning through Interactions with Other Agents: A Surveycited by 3
  4. 2026Neuro-Cognitive Reward Modeling for Human-Centered Autonomous Vehicle Controlcited by 3
  5. 2023Iterative Reward Shaping using Human Feedback for Correcting Reward Misspecificationcited by 2
  6. 2024Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systemscited by 2
  7. 2025A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspectivecited by 2
  8. 2025AEGIS: Human Attention-based Explainable Guidance for Intelligent Vehicle Systemscited by 2
  9. 2025Few-Shot Neuro-Symbolic Imitation Learning for Long-Horizon Planning and Actingcited by 2
  10. 2023Explaining Imitation Learning through Framescited by 1
  11. 2023Genetic Imitation Learning by Reward Extrapolationcited by 1
  12. 2023Toward a Surgeon-in-the-Loop Ophthalmic Robotic Apprentice using Reinforcement and Imitation Learningcited by 1
  13. 2024IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution Historycited by 1
  14. 2024Optimal Policy Learning with Observational Data in Multi-Action Scenarios: Estimation, Risk Preference, and Potential Failurescited by 1
  15. 2024An Efficient Learning Control Framework With Sim-to-Real for String-Type Artificial Muscle-Driven Robotic Systemscited by 1
  16. 2024RILe: Reinforced Imitation Learningcited by 1
  17. 2024Robot See, Robot Do: Imitation Reward for Noisy Financial Environmentscited by 1
  18. 2024Human-like Bots for Tactical Shooters Using Compute-Efficient Sensorscited by 1
  19. 2025FABG : End-to-end Imitation Learning for Embodied Affective Human-Robot Interactioncited by 1
  20. 2025Discrete Contrastive Learning for Diffusion Policies in Autonomous Drivingcited by 1
  21. 2025Restoring Noisy Demonstration for Imitation Learning With Diffusion Modelscited by 1
  22. 2025Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogamescited by 1
  23. 2026Lifelong Imitation Learning with Multimodal Latent Replay and Incremental Adjustmentcited by 1
  24. 2026High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matchingcited by 1
  25. 2022Task-Agnostic Learning to Accomplish New Taskscited by 0
  26. 2023Self-Supervised Adversarial Imitation Learningcited by 0
  27. 2023LuckyMera: a Modular AI Framework for Building Hybrid NetHack Agentscited by 0
  28. 2023Beyond One Model Fits All: Ensemble Deep Learning for Autonomous Vehiclescited by 0
  29. 2024Visual Imitation Learning with Calibrated Contrastive Representationcited by 0
  30. 2024A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observationscited by 0
  31. 2024CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Communitycited by 0
  32. 2024VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Correctionscited by 0
  33. 2024AI-Guided Molecular Simulations in VR: Exploring Strategies for Imitation Learning in Hyperdimensional Molecular Systemscited by 0
  34. 2024Fostering Intrinsic Motivation in Reinforcement Learning with Pretrained Foundation Modelscited by 0
  35. 2024Safe Imitation Learning-based Optimal Energy Storage Systems Dispatch in Distribution Networkscited by 0
  36. 2024Effective Reward Specification in Deep Reinforcement Learningcited by 0
  37. 2024Swarm Behavior Cloningcited by 0
  38. 2025Force-Based Robotic Imitation Learning: A Two-Phase Approach for Construction Assembly Taskscited by 0

50 most cited of 58 All 58 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges
  2. 2024A Survey of Imitation Learning Methods, Environments and Metrics
  3. 2025Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challenges
  4. 2022Interactive Imitation Learning in Robotics: A Survey
  5. 2022Imitation Learning by Estimating Expertise of Demonstrators
  6. 2020Scalable Multi-Task Imitation Learning with Autonomous Improvement
  7. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Play
  8. 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations