Timezone: »
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.
Author Information
Amitay Bar (Technion - Israel Institute of Technology)
Ronen Talmon (Technion - Israel Institute Of Technology)
Ron Meir (Technion Israeli Institute of Technology)
More from the Same Authors
-
2023 Poster: Few-Sample Feature Selection via Feature Manifold Learning »
David Cohen · Tal Shnitzer · Yuval Kluger · Ronen Talmon -
2023 Poster: Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learning »
Ya-Wei Eileen Lin · Ronald Coifman · Gal Mishne · Ronen Talmon -
2021 Poster: Ensemble Bootstrapping for Q-Learning »
Oren Peer · Chen Tessler · Nadav Merlis · Ron Meir -
2021 Spotlight: Ensemble Bootstrapping for Q-Learning »
Oren Peer · Chen Tessler · Nadav Merlis · Ron Meir -
2020 Poster: Discount Factor as a Regularizer in Reinforcement Learning »
Ron Amit · Ron Meir · Kamil Ciosek -
2019 Poster: Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN »
dror freirich · Tzahi Shimkin · Ron Meir · Aviv Tamar -
2019 Oral: Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN »
dror freirich · Tzahi Shimkin · Ron Meir · Aviv Tamar -
2018 Poster: Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory »
Ron Amit · Ron Meir -
2018 Oral: Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory »
Ron Amit · Ron Meir