Poster

Option Discovery in the Absence of Rewards with Manifold Analysis

Amitay Bar · Ronen Talmon · Ron Meir

Keywords: [ Representation Learning ] [ Reinforcement Learning ] [ Spectral Methods ] [ Reinforcement Learning - General ]

[ Abstract ] [ Join Zoom
[ Slides
Please do not share or post zoom links

Abstract:

Options have been shown to be an effective tool in reinforcement learning, facilitating improved exploration and learning. In this paper, we present an approach based on spectral graph theory and derive an algorithm that systematically discovers options without access to a specific reward or task assignment. As opposed to the common practice used in previous methods, our algorithm makes full use of the spectrum of the graph Laplacian. Incorporating modes associated with higher graph frequencies unravels domain subtleties, which are shown to be useful for option discovery. Using geometric and manifold-based analysis, we present a theoretical justification for the algorithm. In addition, we showcase its performance in several domains, demonstrating clear improvements compared to competing methods.

Chat is not available.