Skip to main content
Kent Academic Repository

Reinforcement Learning using Augmented Neural Networks

Shannon, Jack and Grzes, Marek (2018) Reinforcement Learning using Augmented Neural Networks. [Preprint] (doi:10.48550/arXiv.1806.07692) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:98780)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided.
Official URL:
https://doi.org/10.48550/arXiv.1806.07692

Abstract

Neural networks allow Q-learning reinforcement learning agents such as deep Q-networks (DQN) to approximate complex mappings from state spaces to value functions. However, this also brings drawbacks when compared to other function approximators such as tile coding or their generalisations, radial basis functions (RBF) because they introduce instability due to the side effect of globalised updates present in neural networks. This instability does not even vanish in neural networks that do not have any hidden layers. In this paper, we show that simple modifications to the structure of the neural network can improve stability of DQN learning when a multi-layer perceptron is used for function approximation.

Item Type: Preprint
DOI/Identification number: 10.48550/arXiv.1806.07692
Refereed: No
Other identifier: https://arxiv.org/abs/1806.07692
Name of pre-print platform: arXiv
Subjects: Q Science
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Funders: University of Kent (https://ror.org/00xkeyj56)
Depositing User: Marek Grzes
Date Deposited: 06 Dec 2022 10:53 UTC
Last Modified: 05 Nov 2024 13:04 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/98780 (The current URI for this page, for reference purposes)

University of Kent Author Information

  • Depositors only (login required):

Total unique views for this document in KAR since July 2020. For more details click on the image.