# Policy-Calibrated DAgger: Offline Calibrated Noise Injection for Imitation Learning

arXiv: https://arxiv.org/abs/2609.30462 · HTML: https://mlsanity.com/paper/2609.30462/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 42 of its 47 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 30 of 42)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations](https://mlsanity.com/paper/2310.17596/) (2023)
- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation](https://mlsanity.com/paper/2311.01455/) (2023)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning](https://mlsanity.com/paper/2410.24185/) (2024)
- [ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning](https://mlsanity.com/paper/2109.08273/) (2021)
- [SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting](https://mlsanity.com/paper/2409.10161/) (2024)
- [DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning](https://mlsanity.com/paper/2502.16932/) (2025)
- [NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis](https://mlsanity.com/paper/2301.08556/) (2023)
- [Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/2503.24361/) (2025)
- [Grasping with Chopsticks: Combating Covariate Shift in Model-free Imitation Learning for Fine Manipulation](https://mlsanity.com/paper/2011.06719/) (2020)
- [Splat-MOVER: Multi-Stage, Open-Vocabulary Robotic Manipulation via Editable Gaussian Splatting](https://mlsanity.com/paper/2405.04378/) (2024)
- [DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies](https://mlsanity.com/paper/2505.07813/) (2025)
- [Vision in Action: Learning Active Perception from Human Demonstrations](https://mlsanity.com/paper/2506.15666/) (2025)
- [Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning](https://mlsanity.com/paper/2402.17768/) (2024)
- [FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning](https://mlsanity.com/paper/2502.17432/) (2025)
- [Diff-DAgger: Uncertainty Estimation with Diffusion Policy for Robotic Manipulation](https://mlsanity.com/paper/2410.14868/) (2024)
- [Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Corrections](https://mlsanity.com/paper/2506.16685/) (2025)
- [RoboCopilot: Human-in-the-loop Interactive Imitation Learning for Robot Manipulation](https://mlsanity.com/paper/2503.07771/) (2025)
- [To the Noise and Back: Diffusion for Shared Autonomy](https://mlsanity.com/paper/2302.12244/) (2023)
- [Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy Diffusion](https://mlsanity.com/paper/2402.16075/) (2024)
- [A New Approach to Time-Optimal Path Parameterization based on Reachability Analysis](https://mlsanity.com/paper/1707.07239/) (2017)
- [REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer](https://mlsanity.com/paper/2202.05244/) (2022)
- [Visual Robotic Manipulation with Depth-Aware Pretraining](https://mlsanity.com/paper/2401.09038/) (2024)
- [Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning](https://mlsanity.com/paper/2303.06710/) (2023)

## Abstract (arXiv)

Policies trained with imitation learning can accumulate errors over time, causing the robot to drift outside the training distribution. Existing methods mitigate this covariate shift by collecting additional data where the policy fails or is likely to fail. The first places the robot in unsafe conditions and the second requires choosing an appropriate noise distribution to collect new expert demonstrations under that noise. We propose Policy-Calibrated DAgger, a method that makes use of the properties of recent generative policies to estimate the policy's noise offline by using its own predicted action distribution. We measure a diffusion policy's spread of predicted actions at observations along the expert trajectory and measure its closed-loop error relative to a recorded trajectory. To address issues with measuring error in a multimodal action space, we guide the policy towards the trajectory during closed-loop control through partial denoising, and use properties of a diffusion model to unnormalize the measured error as if we did not guide it. We experiment in a scenario where a robot is tasked to reach an engine lever in a cluttered and narrow environment and show results in a 3D photorealistic simulator and a 2D planar reacher environment. We show that our method surpasses policies trained with dataset aggregation without noising and matches the performance of the best noise level in hindsight, without requiring a sweep over noise levels.