Unlocking the Power of Representations in Long-term Novelty-based Exploration
Alaa Saade, Steven Kapturowski, Daniele Calandriello, Charles Blundell, Pablo Sprechmann, Leopoldo Sarra, Oliver Groth, Michal Valko
Abstract
We introduce Robust Exploration via Clustering-based Online Density Estimation (RECODE), a non-parametric method for novelty-based exploration that estimates visitation counts for clusters of states based on their similarity in a chosen embedding space. By adapting classical clustering to the nonstationary setting of Deep RL, RECODE can efficiently track state visitation counts over thousands of episodes. We further propose a novel generalization of the inverse dynamics loss, which leverages masked transformer architectures for multi-step prediction; which in conjunction with \DETOCS achieves a new state-of-the-art in a suite of challenging 3D-exploration tasks in DM-Hard-8. RECODE also sets new state-of-the-art in hard exploration Atari games, and is the first agent to reach the end screen in "Pitfall!"
BibTeX
@inproceedings{
saade2024unlocking,
title={Unlocking the Power of Representations in Long-term Novelty-based Exploration},
author={Alaa Saade and Steven Kapturowski and Daniele Calandriello and Charles Blundell and Pablo Sprechmann and Leopoldo Sarra and Oliver Groth and Michal Valko and Bilal Piot},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=OwtMhMSybu}
}