CUED Publications database

Successor uncertainties: Exploration and uncertainty in temporal difference learning

Janz, D and Hron, J and Mazur, P and Hofmann, K and Hernández-Lobato, JM and Tschiatschek, S (2019) Successor uncertainties: Exploration and uncertainty in temporal difference learning. Advances in Neural Information Processing Systems, 32. ISSN 1049-5258

Full text not available from this repository.

Abstract

© 2019 Neural information processing systems foundation. All rights reserved. Posterior sampling for reinforcement learning (PSRL) is an effective method for balancing exploration and exploitation in reinforcement learning. Randomised value functions (RVF) can be viewed as a promising approach to scaling PSRL. However, we show that most contemporary algorithms combining RVF with neural network function approximation do not possess the properties which make PSRL effective, and provably fail in sparse reward problems. Moreover, we find that propagation of uncertainty, a property of PSRL previously thought important for exploration, does not preclude this failure. We use these insights to design Successor Uncertainties (SU), a cheap and easy to implement RVF algorithm that retains key properties of PSRL. SU is highly effective on hard tabular exploration benchmarks. Furthermore, on the Atari 2600 domain, it surpasses human performance on 38 of 49 games tested (achieving a median human normalised score of 2.09), and outperforms its closest RVF competitor, Bootstrapped DQN, on 36 of those.

Item Type: Article
Uncontrolled Keywords: cs.LG cs.LG stat.ML
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 30 May 2019 01:15
Last Modified: 17 Sep 2020 02:57
DOI: