Unlocking the Power of Representations in Long-term Novelty-based Exploration
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 RECODE 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!".
Keywords
Cite
@article{arxiv.2305.01521,
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},
journal= {arXiv preprint arXiv:2305.01521},
year = {2023}
}