# DADAgger: Disagreement-Augmented Dataset Aggregation

arXiv: https://arxiv.org/abs/2301.01348 · HTML: https://mlsanity.com/paper/2301.01348/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 13 references that are in the map.
- First posted on arXiv 3 Jan 2023.

## Builds on (most cited first, 4 of 4)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning](https://mlsanity.com/paper/2002.06715/) (2020)
- [Query-Efficient Imitation Learning for End-to-End Autonomous Driving](https://mlsanity.com/paper/1605.06450/) (2016)
- [DropoutDAgger: A Bayesian Approach to Safe Imitation Learning](https://mlsanity.com/paper/1709.06166/) (2017)

## Built on by (most cited first, 1 of 1)

- [Policy-Calibrated DAgger: Offline Calibrated Noise Injection for Imitation Learning](https://mlsanity.com/paper/2609.30462/) (2026)

## Abstract (arXiv)

DAgger is an imitation algorithm that aggregates its original datasets by querying the expert on all samples encountered during training. In order to reduce the number of samples queried, we propose a modification to DAgger, known as DADAgger, which only queries the expert for state-action pairs that are out of distribution (OOD). OOD states are identified by measuring the variance of the action predictions of an ensemble of models on each state, which we simulate using dropout. Testing on the Car Racing and Half Cheetah environments achieves comparable performance to DAgger but with reduced expert queries, and better performance than a random sampling baseline. We also show that our algorithm may be used to build efficient, well-balanced training datasets by running with no initial data and only querying the expert to resolve uncertainty.