# Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior

arXiv: https://arxiv.org/abs/2307.14619 · HTML: https://mlsanity.com/paper/2307.14619/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 77 references that are in the map.
- First posted on arXiv 27 Jul 2023.

## Builds on (most cited first, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Is Conditional Generative Modeling all you need for Decision-Making?](https://mlsanity.com/paper/2211.15657/) (2022)
- [Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions](https://mlsanity.com/paper/2209.11215/) (2022)
- [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018)
- [Sliced Score Matching: A Scalable Approach to Density and Score Estimation](https://mlsanity.com/paper/1905.07088/) (2019)
- [IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies](https://mlsanity.com/paper/2304.10573/) (2023)
- [YouTube-8M: A Large-Scale Video Classification Benchmark](https://mlsanity.com/paper/1609.08675/) (2016)
- [Behavior Transformers: Cloning k modes with one stone](https://mlsanity.com/paper/2206.11251/) (2022)
- [Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation](https://mlsanity.com/paper/1710.04615/) (2017)
- [Causal Confusion in Imitation Learning](https://mlsanity.com/paper/1905.11979/) (2019)
- [RoboNet: Large-Scale Multi-Robot Learning](https://mlsanity.com/paper/1910.11215/) (2019)
- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)

## Built on by (most cited first, 30 of 33)

- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [Diffusion Policy Policy Optimization](https://mlsanity.com/paper/2409.00588/) (2024)
- [Compositional Foundation Models for Hierarchical Planning](https://mlsanity.com/paper/2309.08587/) (2023)
- [PoCo: Policy Composition from and for Heterogeneous Robot Learning](https://mlsanity.com/paper/2402.02511/) (2024)
- [Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories](https://mlsanity.com/paper/2505.21851/) (2025)
- [JUICER: Data-Efficient Imitation Learning for Robotic Assembly](https://mlsanity.com/paper/2404.03729/) (2024)
- [Much Ado About Noising: Dispelling the Myths of Generative Robotic Control](https://mlsanity.com/paper/2512.01809/) (2025)
- [CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning](https://mlsanity.com/paper/2310.12972/) (2023)
- [A Theory of Learning with Autoregressive Chain of Thought](https://mlsanity.com/paper/2503.07932/) (2025)
- [One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow](https://mlsanity.com/paper/2511.13035/) (2025)
- [Diffusing States and Matching Scores: A New Framework for Imitation Learning](https://mlsanity.com/paper/2410.13855/) (2024)
- [Robot Fleet Learning via Policy Merging](https://mlsanity.com/paper/2310.01362/) (2023)
- [Active Fine-Tuning of Multi-Task Policies](https://mlsanity.com/paper/2410.05026/) (2024)
- [Hybrid Reinforcement Learning from Offline Observation Alone](https://mlsanity.com/paper/2406.07253/) (2024)
- [Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error](https://mlsanity.com/paper/2504.01766/) (2025)
- [Inverse Q-Learning Done Right: Offline Imitation Learning in Qπ-Realizable MDPs](https://mlsanity.com/paper/2505.19946/) (2025)
- [The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation](https://mlsanity.com/paper/2406.11686/) (2024)
- [Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory Distillation](https://mlsanity.com/paper/2506.07822/) (2025)
- [EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes](https://mlsanity.com/paper/2508.00180/) (2025)
- [How Well do Diffusion Policies Learn Kinematic Constraint Manifolds?](https://mlsanity.com/paper/2510.01404/) (2025)
- [To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning](https://mlsanity.com/paper/2510.03207/) (2025)
- [TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning](https://mlsanity.com/paper/2605.12236/) (2026)
- [Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with Demonstrations](https://mlsanity.com/paper/2412.01114/) (2024)
- [A Model-Based Approach to Imitation Learning through Multi-Step Predictions](https://mlsanity.com/paper/2504.13413/) (2025)
- [A Test-Function Approach to Incremental Stability](https://mlsanity.com/paper/2507.00695/) (2025)
- [Continuous Vision-Language-Action Co-Learning with Semantic-Physical Alignment for Behavioral Cloning](https://mlsanity.com/paper/2511.14396/) (2025)
- [GrOMP: Grasped Object Manifold Projection for Multimodal Imitation Learning of Manipulation](https://mlsanity.com/paper/2512.03347/) (2025)
- [Flow as Flow: Modeling Robot Velocity Fields as Probability Velocity Fields for Flow-Based Object Manipulation](https://mlsanity.com/paper/2606.23090/) (2026)
- [Learning in Hybrid Active Inference Models](https://mlsanity.com/paper/2409.01066/) (2024)
- [Improved Sample Complexity of Imitation Learning for Barrier Model Predictive Control](https://mlsanity.com/paper/2410.00859/) (2024)

## Abstract (arXiv)

We propose a theoretical framework for studying behavior cloning of complex expert demonstrations using generative modeling. Our framework invokes low-level controllers - either learned or implicit in position-command control - to stabilize imitation around expert demonstrations. We show that with (a) a suitable low-level stability guarantee and (b) a powerful enough generative model as our imitation learner, pure supervised behavior cloning can generate trajectories matching the per-time step distribution of essentially arbitrary expert trajectories in an optimal transport cost. Our analysis relies on a stochastic continuity property of the learned policy we call "total variation continuity" (TVC). We then show that TVC can be ensured with minimal degradation of accuracy by combining a popular data-augmentation regimen with a novel algorithmic trick: adding augmentation noise at execution time. We instantiate our guarantees for policies parameterized by diffusion models and prove that if the learner accurately estimates the score of the (noise-augmented) expert policy, then the distribution of imitator trajectories is close to the demonstrator distribution in a natural optimal transport distance. Our analysis constructs intricate couplings between noise-augmented trajectories, a technique that may be of independent interest. We conclude by empirically validating our algorithmic recommendations, and discussing implications for future research directions for better behavior cloning with generative modeling.