TY - GEN
T1 - Supervised reinforcement learning in discrete environment domains
AU - Jensen, Boris
AU - Ortiz-Arroyo, Daniel
AU - Cruz-Cortés, Nareli
AU - Rodríguez-Henríquez, Francisco
PY - 2010
Y1 - 2010
N2 - This paper describes a supervised reinforcement learning-based model for discrete environment domains. The model was tested within the domain of backgammon game. Our results show that a supervised actor-critic based learning model is capable of improving the initial performance and then eventually reach similar performance levels as those obtained by TD-Gammon, an artificial neural network player (ANN) trained by temporal differences.
AB - This paper describes a supervised reinforcement learning-based model for discrete environment domains. The model was tested within the domain of backgammon game. Our results show that a supervised actor-critic based learning model is capable of improving the initial performance and then eventually reach similar performance levels as those obtained by TD-Gammon, an artificial neural network player (ANN) trained by temporal differences.
KW - Actorcritic
KW - Automata player
KW - Machine learning
KW - Reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=79952753576&partnerID=8YFLogxK
U2 - 10.1109/NABIC.2010.5716276
DO - 10.1109/NABIC.2010.5716276
M3 - Contribución a la conferencia
AN - SCOPUS:79952753576
SN - 9781424473762
T3 - Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010
SP - 215
EP - 220
BT - Proceedings - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010
T2 - 2010 2nd World Congress on Nature and Biologically Inspired Computing, NaBIC 2010
Y2 - 15 December 2010 through 17 December 2010
ER -