$```$

# Global Parameters $($Do not change these parameter names$)$

STUDENTID $=202162070$ # Enter your student ID $($You may change this to try different start and goal positions$)$

GRID$\_$SIZE $=5$ #

ACTIONS $=4$ DO NOT CHANGE

EPISODES $=5000$ # CHANGE to an appropriate number to ensure agent learns to find the optimal path and that Q table

# Do not change number of episodes parameter$/$variable anywhere else in the code

ALPHA $=0\mathrm{.}1$ # DO NOT CHANGE

EPSILON $=0\mathrm{.}2$ # DO NOT CHANGE

GAMMA $=0\mathrm{.}9$ # DO NOT CHANGE

$``````$

# TASK $1-$ Complete the function to get next state based on given action

def get$\_$next$\_$state$($current$\_$state$\_$pos, action, grid$\_$size$)$: # Ensure grid$\_$size is passed

row, column $=$ current$\_$state$\_$pos # row and column are integers

if action $==0$ and row $>0$: # Move up

row $-=1$ # Move one row up

elif action $==1$ and row $$ grid$\_$size $-1$: # Move down

row $+=1$ # Move one row down

elif action $==2$ and column $>0$: # Move left

column $-=1$ # Move one column to the left

elif action $==3$ and column $$ grid$\_$size $-1$: # Move right

column $+=1$ # Move one column to the right

return $($row$,$ column$)$ # Ensure it returns a tuple of $($row$,$ column$)$

$```$ Task I, $(\backslash$$$8$ Points$)$ Teskget$\_$rext stalef$($ function implemenlation $(0/$B$)$