Novelty-organizing team of classifiers - A team-individual multi-objective approach to reinforcement learning

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

In reinforcement learning, there are basically two spaces to search: value-function space and policy space. Consequently, there are two fitness functions each with their associated trade-offs. However, the problem is still perceived as a single-objective one. Here a multi-objective reinforcement learning algorithm is proposed with a structured novelty map population evolving feedforward neural models. It outperforms a gradient based continuous input-output state-of-art algorithm in two problems. Contrary to the gradient based algorithm, the proposed one solves both problems with the same parameters and smaller variance of results. Moreover, the results are comparable even with other discrete action algorithms of the literature as well as neuroevolution methods such as NEAT. The proposed method brings also the novelty map population concept, i.e., a novelty map-based population which is less sensitive to the input distribution and therefore more suitable to create the state space. In fact, the novelty map framework is shown to be less dynamic and more resource efficient than variants of the self-organizing map.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
PublisherSociety of Instrument and Control Engineers (SICE)
Pages1785-1792
Number of pages8
ISBN (Electronic)9784907764463
DOIs
Publication statusPublished - Oct 23 2014
Event2014 53rd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2014 - Sapporo, Japan
Duration: Sep 9 2014Sep 12 2014

Publication series

NameProceedings of the SICE Annual Conference

Other

Other2014 53rd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2014
Country/TerritoryJapan
CitySapporo
Period9/9/149/12/14

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Novelty-organizing team of classifiers - A team-individual multi-objective approach to reinforcement learning'. Together they form a unique fingerprint.

Cite this