id: 70709428
dt: a
an: 70709428
au: Maeda, Yoichiro; Hanaka, Satoshi
ti: Differential reinforcement-type shaping Q-learning method based on animal
    training for autonomous mobile robot
so: FUZZ-IEEE, 2066-2071 (2008).
py: 2008
pu: 
la: EN
cc: 
ut: 
ci: 
li: doi:10.1109/FUZZY.2008.4630654