Symbiogenesis in learning classifier systems

Tomlinson, Andy; Bull, Larry

Andy Tomlinson

Lawrence Bull Larry.Bull@uwe.ac.uk
School Director (Research & Enterprise) and Professor

Tomlinson, A., & Bull, L. (2001). Symbiogenesis in learning classifier systems. Artificial Life, 7(1), 33-61. https://doi.org/10.1162/106454601300328016

Journal Article Type	Article
Publication Date	Jan 1, 2001
Deposit Date	Jan 22, 2010
Publicly Available Date	May 13, 2016
Journal	Artificial Life
Print ISSN	1064-5462
Publisher	Massachusetts Institute of Technology Press (MIT Press)
Peer Reviewed	Peer Reviewed
Volume	7
Issue	1
Pages	33-61
DOI	https://doi.org/10.1162/106454601300328016
Keywords	animat, cooperation, evolution, genetic linkage, symbiosis
Public URL	https://uwe-repository.worktribe.com/output/1088462
Publisher URL	http://dx.doi.org/10.1162/106454601300328016
Additional Information	Additional Information : The class of problems which require the memory of previous inputs or actions - non-Markov problems - remain amongst the most difficiult for machine learning techniques. This paper describes how an evolutionary computing mechanism based on the hypothesised process leading to the evolution of eukaryotic cells from simpler organisms enables the solution of such problems for reinforcement learning. The research was undertaken as part of an EPSRC project (GR/R067848/01) exploring the use of Learning Classifier Systems for distributed road traffic junction control - a task in which memory is potentially useful.