2.4 本题在中文版的书中翻译可能不是很准确(个人推断),我寻找了英文原题如下
If the step-size parameters,
α
n
, are not constant, then the estimate
Q
n
is a weighted average of
previously received rewards with a weighting difffferent from that given by (2.6). What is the weighting on each prior reward for the general case, analogous to (2.6), in terms of the sequence of step-size parameters?
我觉得原题问的应该是上一步奖励的权值是多少,即2.6中R的系数。但得出结论前,我们需要对公式2.6做一下推广: