A subject with an alpha045 and has an actionvalue for symbol

A subject with an alpha=0.45 and has an action-value for symbol A = 0.75 and symbol B = 0.65. The subject selects B and receives a reward of 1.

After this trial, which symbol is the subject more likely to select.

Please explain

Solution

Answer-

Here we have,

action-value for symbol A = 0.75

action-value for symbol B = 0.65

and, alpha = 0.45

The delta for symbol B is =  action value for symbol A + action value of aymbol B/ alpha

=  0.75 + 0.65/0.45

=  1.40/0.45

= 2.3

After this trial symbol B is more likely to select.