English

An Adversarial Objective for Scalable Exploration

Robotics 2020-11-12 v4 Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning

Abstract

Model-based curiosity combines active learning approaches to optimal sampling with the information gain based incentives for exploration presented in the curiosity literature. Existing model-based curiosity methods look to approximate prediction uncertainty with approaches which struggle to scale to many prediction-planning pipelines used in robotics tasks. We address these scalability issues with an adversarial curiosity method minimizing a score given by a discriminator network. This discriminator is optimized jointly with a prediction model and enables our active learning approach to sample sequences of observations and actions which result in predictions considered the least realistic by the discriminator. We demonstrate progressively increasing advantages as compute is restricted of our adversarial curiosity approach over leading model-based exploration strategies in simulated environments. We further demonstrate the ability of our adversarial curiosity method to scale to a robotic manipulation prediction-planning pipeline where we improve sample efficiency and prediction performance for a domain transfer problem.

Keywords

Cite

@article{arxiv.2003.06082,
  title  = {An Adversarial Objective for Scalable Exploration},
  author = {Bernadette Bucher and Karl Schmeckpeper and Nikolai Matni and Kostas Daniilidis},
  journal= {arXiv preprint arXiv:2003.06082},
  year   = {2020}
}

Comments

Additional visualizations of our results are available on our website at https://sites.google.com/view/action-for-better-prediction . Bernadette Bucher and Karl Schmeckpeper contributed equally

R2 v1 2026-06-23T14:13:30.466Z