TY - GEN
T1 - Modulating reinforcement-learning parameters using agent emotions
AU - Von Haugwitz, Rickard
AU - Kitamura, Yoshifumi
AU - Takashima, Kazuki
PY - 2012/12/1
Y1 - 2012/12/1
N2 - An actor-critic reinforcement-learning algorithm using a radial-basis-function network for approximation of the actor and the critic was run on a small-scale multi-agent system with an initially unpredictably hostile environment. The performance of two approaches was compared: having fixed learning parameters, and using modulated parameters that were allowed to deviate from their base values depending on the simulated emotional state of the agent. The latter approach was shown to give marginally better performance once the distracting hostile elements were removed from the environment. This seems to indicate that emotion-modulated learning may lead to somewhat closer approximation of the optimal policy in a difficult environment, by focusing learning on more useful input and avoiding pursuing suboptimal strategies.
AB - An actor-critic reinforcement-learning algorithm using a radial-basis-function network for approximation of the actor and the critic was run on a small-scale multi-agent system with an initially unpredictably hostile environment. The performance of two approaches was compared: having fixed learning parameters, and using modulated parameters that were allowed to deviate from their base values depending on the simulated emotional state of the agent. The latter approach was shown to give marginally better performance once the distracting hostile elements were removed from the environment. This seems to indicate that emotion-modulated learning may lead to somewhat closer approximation of the optimal policy in a difficult environment, by focusing learning on more useful input and avoiding pursuing suboptimal strategies.
UR - http://www.scopus.com/inward/record.url?scp=84877830310&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84877830310&partnerID=8YFLogxK
U2 - 10.1109/SCIS-ISIS.2012.6505340
DO - 10.1109/SCIS-ISIS.2012.6505340
M3 - Conference contribution
AN - SCOPUS:84877830310
SN - 9781467327428
T3 - 6th International Conference on Soft Computing and Intelligent Systems, and 13th International Symposium on Advanced Intelligence Systems, SCIS/ISIS 2012
SP - 1281
EP - 1285
BT - 6th International Conference on Soft Computing and Intelligent Systems, and 13th International Symposium on Advanced Intelligence Systems, SCIS/ISIS 2012
T2 - 2012 Joint 6th International Conference on Soft Computing and Intelligent Systems, SCIS 2012 and 13th International Symposium on Advanced Intelligence Systems, ISIS 2012
Y2 - 20 November 2012 through 24 November 2012
ER -