1. Suppose the data in the table shows the Q value for the current Game Nim. On the next turn it is assumed that you win because the remainder of the match is always taken by your opponent. The group's task is to update the table using a) temporal differences approach

Transcribed Image Text:

Matches picked up 1 23 3 2 0.999 -0.141 -0.994 0.999 0.000 -0.984 State (= number of matches left) 4 5 6 7 0.484 -0.122 0.155 0.000 -0.108 -0.276 -0.171 0.000 1.000 -0.070 -0.080 0.000 8 0.272 0.252 0.426 Matches picked up 1 23 3 2 0.999 -0.141 -0.994 0.999 0.000 -0.984 State (= number of matches left) 4 5 6 7 0.484 -0.122 0.155 0.000 -0.108 -0.276 -0.171 0.000 1.000 -0.070 -0.080 0.000 8 0.272 0.252 0.426