TY - GEN
T1 - Hybrid of evolution and reinforcement learning for othello players
AU - Kim, Kyung Joong
AU - Choi, Heejin
AU - Cho, Sung Bae
PY - 2007
Y1 - 2007
N2 - Although the reinforcement learning and evolutionary algorithm show good results in board evaluation optimization, the hybrid of both approaches is rarely addressed in the literature. In this paper, the evolutionary algorithm is boosted using resources from the reinforcement learning. 1) The initialization of initial population using solution optimized by temporal difference learning 2) Exploitation of domain knowledge extracted from reinforcement learning. Experiments on Othello game strategies show that the proposed methods can effectively search the solution space and improve the performance.
AB - Although the reinforcement learning and evolutionary algorithm show good results in board evaluation optimization, the hybrid of both approaches is rarely addressed in the literature. In this paper, the evolutionary algorithm is boosted using resources from the reinforcement learning. 1) The initialization of initial population using solution optimized by temporal difference learning 2) Exploitation of domain knowledge extracted from reinforcement learning. Experiments on Othello game strategies show that the proposed methods can effectively search the solution space and improve the performance.
UR - http://www.scopus.com/inward/record.url?scp=34548767008&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34548767008&partnerID=8YFLogxK
U2 - 10.1109/CIG.2007.368099
DO - 10.1109/CIG.2007.368099
M3 - Conference contribution
AN - SCOPUS:34548767008
SN - 1424407095
SN - 9781424407095
T3 - Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007
SP - 203
EP - 209
BT - Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007
T2 - 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007
Y2 - 1 April 2007 through 5 April 2007
ER -