TY  - RPRT
TI  - Control of exploitation-exploration meta-parameter in reinforcement learning.
AU  - Shin Ishii
AU  - Wako Yoshida
AU  - Junichiro Yoshimoto
DO  - 10.1016/s0893-6080(02)00056-4
UR  - https://pubmed.ncbi.nlm.nih.gov/12371519/
ID  - 12371519
ER  -