Parameterless-Growing-SOM and Its Application to a Voice Instruction Learning System

Table 1

Q-value table. Each unit of Action Map has a $Q_t(s_t,a_t(i))$ value corresponding to an action.

$s_t$	$a_t(1)$	$a_t(2)$	$a_t(i)$	$a_t(K)$
$1$	$6$	$2$	$-8$	$0$
$2$	$10$	$1$	$0$	$1$
$\cdots$
$N\times M$	$0$	$2$	$7$	$2$