Poster
in
Workshop: Agent Learning in Open-Endedness Workshop
Unlocking the Power of Representations in Long-term Novelty-based Exploration
Steven Kapturowski · Alaa Saade · Daniele Calandriello · Charles Blundell · Pablo Sprechmann · Leopoldo Sarra · Oliver Groth · Michal Valko · Bilal Piot
Keywords: [ intrinsic motivation ] [ Representation Learning ] [ Exploration ] [ Deep Reinforcement Learning ]
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!