Your Task $($part $2)$:

Now that you've implemented q$-$learning for one task, you will move to the mountain car task.

Instead of $2$ actions $($left$,$ right$),$ this task has three $($left$,$ null, right$).$ The task also has different

state variables $($only $2)$

$?x$ : the location of the robot is the left, $-\mathrm{.}45$ is approximately the valley, $0\mathrm{.}6$ is the

rightmost part of the board, $0\mathrm{.}5$ is the location of the flag$)$

$?$ xdot: the velocity of the robot $($this can go from $-0\mathrm{.}07$ to $0\mathrm{.}07)$

This will require you to change the number of bins for state descritization as well as the

alpha and gamma values. Additionally, you need to implement the exploration vs

exploitation part for this problem as well.

Once your model is trained it will be saved the Q$-$table as 'car.npy$\text{'}$ file. Make sure to that you

don't change this file name.