# MEGA-DAgger: Imitation Learning with Multiple Imperfect Experts

arXiv: https://arxiv.org/abs/2303.00638 · HTML: https://mlsanity.com/paper/2303.00638/

## Key facts

- Cited by 18 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 16 of its 41 references that are in the map.
- First posted on arXiv 1 Mar 2023.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 16 of 16)

- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Control Barrier Function Based Quadratic Programs for Safety Critical Systems](https://mlsanity.com/paper/1609.06408/) (2016)
- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations](https://mlsanity.com/paper/1904.06387/) (2019)
- [Imitation Learning from Imperfect Demonstration](https://mlsanity.com/paper/1901.09387/) (2019)
- [ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning](https://mlsanity.com/paper/2109.08273/) (2021)
- [EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning](https://mlsanity.com/paper/1807.08364/) (2018)
- [Query-Efficient Imitation Learning for End-to-End Autonomous Driving](https://mlsanity.com/paper/1605.06450/) (2016)
- [Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing](https://mlsanity.com/paper/2202.07008/) (2022)
- [LazyDAgger: Reducing Context Switching in Interactive Imitation Learning](https://mlsanity.com/paper/2104.00053/) (2021)
- [Deep Learning in Robotics: A Review of Recent Research](https://mlsanity.com/paper/1707.07217/) (2017)
- [Learn-to-Race: A Multimodal Control Environment for Autonomous Racing](https://mlsanity.com/paper/2103.11575/) (2021)
- [Exploring Imitation Learning for Autonomous Driving with Feedback Synthesizer and Differentiable Rasterization](https://mlsanity.com/paper/2103.01882/) (2021)
- [A Benchmark Comparison of Imitation Learning-based Control Policies for Autonomous Racing](https://mlsanity.com/paper/2209.15073/) (2022)
- [Enhancing Feasibility and Safety of Nonlinear Model Predictive Control with Discrete-Time Control Barrier Functions](https://mlsanity.com/paper/2105.10596/) (2021)
- [Indy Autonomous Challenge -- Autonomous Race Cars at the Handling Limits](https://mlsanity.com/paper/2202.03807/) (2022)

## Built on by (most cited first, 18 of 18)

- [Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior](https://mlsanity.com/paper/2307.14619/) (2023)
- [The Pitfalls of Imitation Learning when Actions are Continuous](https://mlsanity.com/paper/2503.09722/) (2025)
- [Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model](https://mlsanity.com/paper/2404.04619/) (2024)
- [Autonomous Navigation of Unmanned Vehicle Through Deep Reinforcement Learning](https://mlsanity.com/paper/2407.18962/) (2024)
- [Dynamic Rank Adjustment in Diffusion Policies for Efficient and Flexible Training](https://mlsanity.com/paper/2502.03822/) (2025)
- [DexHiL: A Human-in-the-Loop Framework for Vision-Language-Action Model Post-Training in Dexterous Manipulation](https://mlsanity.com/paper/2603.09121/) (2026)
- [PRISM-DP: Spatial Pose-based Observations for Diffusion-Policies via Segmentation, Mesh Generation, and Pose Tracking](https://mlsanity.com/paper/2504.20359/) (2025)
- [IIFL: Implicit Interactive Fleet Learning from Heterogeneous Human Supervisors](https://mlsanity.com/paper/2306.15228/) (2023)
- [Interactive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A Survey](https://mlsanity.com/paper/2506.00098/) (2025)
- [Developing Path Planning with Behavioral Cloning and Proximal Policy Optimization for Path-Tracking and Static Obstacle Nudging](https://mlsanity.com/paper/2409.05289/) (2024)
- [Optimizing Active Perception for Learning Simultaneous Viewpoint Selection and Manipulation with Diffusion Policy](https://mlsanity.com/paper/2409.14615/) (2024)
- [Arnold: A multi-task, multi-embodiment muscle transformer policy](https://mlsanity.com/paper/2508.18066/) (2025)
- [NeRF-Aug: Data Augmentation for Robotics with Neural Radiance Fields](https://mlsanity.com/paper/2411.02482/) (2024)
- [GrOMP: Grasped Object Manifold Projection for Multimodal Imitation Learning of Manipulation](https://mlsanity.com/paper/2512.03347/) (2025)
- [Imitation Learning for Combinatorial Optimisation under Uncertainty](https://mlsanity.com/paper/2601.05383/) (2026)
- [Oracle-Guided Soft Shielding for Safe Move Prediction in Chess](https://mlsanity.com/paper/2603.08506/) (2026)
- [Behavior-Constrained Reinforcement Learning with Receding-Horizon Credit Assignment for High-Performance Control](https://mlsanity.com/paper/2604.03023/) (2026)
- [Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Traffic](https://mlsanity.com/paper/2604.12857/) (2026)

## Abstract (arXiv)

Imitation learning has been widely applied to various autonomous systems thanks to recent development in interactive algorithms that address covariate shift and compounding errors induced by traditional approaches like behavior cloning. However, existing interactive imitation learning methods assume access to one perfect expert. Whereas in reality, it is more likely to have multiple imperfect experts instead. In this paper, we propose MEGA-DAgger, a new DAgger variant that is suitable for interactive learning with multiple imperfect experts. First, unsafe demonstrations are filtered while aggregating the training data, so the imperfect demonstrations have little influence when training the novice policy. Next, experts are evaluated and compared on scenarios-specific metrics to resolve the conflicted labels among experts. Through experiments in autonomous racing scenarios, we demonstrate that policy learned using MEGA-DAgger can outperform both experts and policies learned using the state-of-the-art interactive imitation learning algorithms such as Human-Gated DAgger. The supplementary video can be found at urlhttps://youtu.be/wPCht31MHrw.