en
Scientific article
English

Self-organizing maps for storage and transfer of knowledge in reinforcement learning

Published inAdaptive behavior, vol. 27, no. 2, p. 111-126
Publication date2018-12-20
First online date2018-12-20
Abstract

The idea of reusing or transferring information from previously learned tasks (source tasks) for the learning of new tasks (target tasks) has the potential to significantly improve the sample efficiency of a reinforcement learning agent. In this work, we describe a novel approach for reusing previously acquired knowledge by using it to guide the exploration of an agent while it learns new tasks. In order to do so, we employ a variant of the growing self-organizing map algorithm, which is trained using a measure of similarity that is defined directly in the space of the vectorized representations of the value functions. In addition to enabling transfer across tasks, the resulting map is simultaneously used to enable the efficient storage of previously acquired task knowledge in an adaptive and scalable manner. We empirically validate our approach in a simulated navigation environment and also demonstrate its utility through simple experiments using a mobile micro-robotics platform. In addition, we demonstrate the scalability of this approach and analytically examine its relation to the proposed network growth mechanism. Furthermore, we briefly discuss some of the possible improvements and extensions to this approach, as well as its relevance to real-world scenarios in the context of continual learning.

eng
Keywords
  • Reinforcement learning
  • Transfer learning
Affiliation Not a UNIGE publication
Citation (ISO format)
GEORGE KARIMPANAL, Thommen, BOUFFANAIS, Roland. Self-organizing maps for storage and transfer of knowledge in reinforcement learning. In: Adaptive behavior, 2018, vol. 27, n° 2, p. 111–126. doi: 10.1177/1059712318818568
Main files (1)
Article (Published version)
accessLevelRestricted
Identifiers
ISSN of the journal1059-7123
9views
0downloads

Technical informations

Creation04/03/2024 6:15:23 AM
First validation04/03/2024 12:08:49 PM
Update time04/03/2024 12:08:49 PM
Status update04/03/2024 12:08:49 PM
Last indexation04/03/2024 12:09:10 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack