mlsanityData to 14 Oct 2026

Imitating Human Behaviour with Diffusion Models

arXiv 2301.10677 ↗First posted 25 Jan 2023cs.AI cs.LG stat.MLcited by 263

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

Diffusion models have emerged as powerful generative models in the text-to-image domain. This paper studies their application as observation-to-action models for imitating human behaviour in sequential environments. Human behaviour is stochastic and multimodal, with structured correlations between action dimensions. Meanwhile, standard modelling choices in behaviour cloning are limited in their expressiveness and may introduce bias into the cloned policy. We begin by pointing out the limitations of these choices. We then propose that diffusion models are an excellent fit for imitating human behaviour, since they learn an expressive distribution over the joint action space. We introduce several innovations to make diffusion models suitable for sequential environments; designing suitable architectures, investigating the role of guidance, and developing reliable sampling strategies. Experimentally, diffusion models closely match human demonstrations in a simulated robotic control task and a modern 3D gaming environment.

Key facts. Cited by 263 papers in the map (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 33 of its 44 references that are in the map. First posted on arXiv 25 Jan 2023.

Builds on

33 of 44 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Is Conditional Generative Modeling all you need for Decision-Making?28 Nov
  2. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning12 Aug

Other references · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  6. 2022Classifier-Free Diffusion Guidancecited by 5,847
  7. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  8. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  9. 2016Generative Adversarial Imitation Learningcited by 1,597
  10. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  11. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  12. 2022A Generalist Agentcited by 808
19 more
  1. 2021Implicit Behavioral Cloningcited by 452
  2. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
  3. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learningcited by 384
  4. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  5. 2022Behavior Transformers: Cloning k modes with one stonecited by 304
  6. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  7. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 223
  8. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 200
  9. 2019A Divergence Minimization Perspective on Imitation Learning Methodscited by 190
  10. 2020Open Problems in Cooperative AIcited by 168
  11. 2021Collaborating with Humans without Human Datacited by 142
  12. 2020Parrot: Data-Driven Behavioral Priors for Reinforcement Learningcited by 138
  13. 2019Imitation Learning as f-Divergence Minimizationcited by 123
  14. 2020Primal Wasserstein Imitation Learningcited by 121
  15. 2021What Matters for Adversarial Imitation Learning?cited by 70
  16. 2020Limitations of Autoregressive Models and Their Alternativescited by 55
  17. 2021Counter-Strike Deathmatch with Large-Scale Behavioural Cloningcited by 50
  18. 2020Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kingscited by 18
  19. 2021Hyperparameter Selection for Imitation Learningcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 56; 2024: 84; 2025: 69; 2026: 54.

263 papers.

Sort:

By area:

  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  2. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 691
  3. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 422
  4. 2023IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policiescited by 325
  5. 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 300
  6. 2023Aligning Text-to-Image Diffusion Models with Reward Backpropagationcited by 288
  7. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 282
  8. 2024Diffusion Policy Policy Optimizationcited by 280
  9. 2023NoMaD: Goal Masked Diffusion Policies for Navigation and Explorationcited by 248
  10. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policiescited by 236
  11. 2025Real-Time Execution of Action Chunking Flow Policiescited by 216
  12. 2024RoboDreamer: Learning Compositional World Models for Robot Imaginationcited by 195
38 more
  1. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 181
  2. 2024RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulationcited by 175
  3. 2024VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Taskscited by 175
  4. 2024Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillationcited by 166
  5. 2024Behavior Generation with Latent Actionscited by 160
  6. 2023Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learningcited by 149
  7. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representationscited by 116
  8. 2023Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learningcited by 115
  9. 2023Policy Representation via Diffusion Probability Model for Reinforcement Learningcited by 112
  10. 2023Parallel Sampling of Diffusion Modelscited by 112
  11. 2024FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulationcited by 104
  12. 2023Synthetic Experience Replaycited by 101
  13. 2023Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learningcited by 100
  14. 2023Diffusion Models for Reinforcement Learning: A Surveycited by 91
  15. 2023Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Modelscited by 91
  16. 2024From Imitation to Refinement -- Residual RL for Precise Assemblycited by 90
  17. 2023HumanMAC: Masked Motion Completion for Human Motion Predictioncited by 81
  18. 2023MADiff: Offline Multi-agent Learning with Diffusion Modelscited by 75
  19. 2023XSkill: Cross Embodiment Skill Discoverycited by 75
  20. 2025Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policycited by 74
  21. 2024Simple Hierarchical Planning with Diffusioncited by 73
  22. 2024An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimizationcited by 73
  23. 2024The Ingredients for Robotic Diffusion Transformerscited by 73
  24. 2023Score Regularized Policy Optimization through Diffusion Behaviorcited by 71
  25. 2023VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Modelscited by 68
  26. 2024Equivariant Diffusion Policycited by 66
  27. 2024Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theorycited by 63
  28. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 60
  29. 2024ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulationcited by 57
  30. 2023Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimizationcited by 56
  31. 2024Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Modelscited by 56
  32. 2025Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Modelscited by 56
  33. 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrationscited by 53
  34. 2023Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulationcited by 52
  35. 2024AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policiescited by 50
  36. 2023Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvementcited by 49
  37. 2023EDMP: Ensemble-of-costs-guided Diffusion for Motion Planningcited by 49
  38. 2024RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Controlcited by 48

50 most cited of 263 All 263 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations
  2. 2024Generation of Complex 3D Human Motion by Temporal and Spatial Composition of Diffusion Models
  3. 2025DIRIGENt: End-To-End Robotic Imitation of Human Demonstrations Based on a Diffusion Model
  4. 2024Towards motion from video diffusion models
  5. 2025Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
  6. 2025AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis
  7. 2024Unpacking the Individual Components of Diffusion Policy
  8. 2026Guided Discovery of New Behaviors using Diffusion Policies