OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Genetically-regulated Neuromodulation Facilitates Multi-Task Reinforcement Learning

Cussat-Blanc, Sylvain and Harrington, Kyle Genetically-regulated Neuromodulation Facilitates Multi-Task Reinforcement Learning. (2015) In: Genetic and Evolutionary Computation Conference (GECCO 2015), 11 July 2015 - 15 July 2015 (Madrid, Spain).

(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader

Official URL: http://dx.doi.org/10.1145/2739480.2754730


In this paper, we use a gene regulatory network (GRN) to regulate a reinforcement learning controller, the State- Action-Reward-State-Action (SARSA) algorithm. The GRN serves as a neuromodulator of SARSA's learning parame- ters: learning rate, discount factor, and memory depth. We have optimized GRNs with an evolutionary algorithm to regulate these parameters on specific problems but with no knowledge of problem structure. We show that genetically- regulated neuromodulation (GRNM) performs comparably or better than SARSA with fixed parameters. We then ex- tend the GRNM SARSA algorithm to multi-task problem generalization, and show that GRNs optimized on multi- ple problem domains can generalize to previously unknown problems with no further optimization.

Item Type:Conference or Workshop Item (Paper)
Additional Information:ISBN: 978-1-4503-3472-3
HAL Id:hal-04077782
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Other partners > Harvard Medical School - HMS (USA)
Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Laboratory name:
Deposited On:23 May 2016 14:09

Repository Staff Only: item control page