Using Q$-$learning, the initial values in the Q$-$Table are as follows

$Q[S1,A1]=15$

$Q[S1,A2]=10$

$Q[S2,A1]=10$

$Q[S2,A2]=-5$

What is the result of the $Q$ table after running the following

$?$four sequence of steps

Please note that the answer of each step will affect

$.$the steps after it

Use the discount factor of $0\mathrm{.}5$

:Step $1$

What are the new values in the $Q$ table given that

Current state:S$1$

Action: A$1$

Next state: S$1$

Reward: $-10$ What are the new values in the $Q$ table given that

Current state:S$1$

Action: A$2$

Next state: S$2$

Reward: $-10$

:Step $3$

What are the new values in the $Q$ table given that

Current state:S$2$

Action: A$1$

Next state: S$1$

Reward: $20$ :Step $4$

What are the new values in the $Q$ table given that

Current state:S$1$

Action: A$2$

Next state: S$1$

Reward: $-10$