Please write the code for part one in

python. No pusedo code please.

Objectives:

python. No pusedo code please.

To implement a reinforcement based on task$-$based rewards

To take a continuous environment and discretize it so that it is suitable for a

reinforcement learning task

This is the CartPole task. The idea here is to balance this pole using a one$-$dimensional robot $($it

can only move left and right$).$ The robot's state has $4$ components:

$?x$ : the location of the robot $(0$ is the center, $-2\mathrm{.}4$ is the leftmost part of the board, $2\mathrm{.}4$ is

the rightmost part of the board$)$

OpenAI Gym:

You do not have to implement the problem domain yourself, there is a resource called openAl

gym which has a set of common training examples. Gym can be installed with the following

command:After running the provided command, you may also be asked to install some additional

packages for the video encoding. You'll see an error message with instructions to follow.

State Discretization:

We will discretize the space in order to simplify the reinforcement learning algorithm. One

example can be as follows:

$?$ x: $($one bucket for one for random$()Qxp$

Choose random action

Else:

Choose action that gives max $Q$ value

Your Task $(part2)$:

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

Instead $of2$ actions $(left,$ right$),$ this task has three $(left,$ null, right$).$ The task also has different

state variables $(only2)$

$?x$ : the location $of$ the robot $(-1\mathrm{.}2is$ the left, $-\mathrm{.}45is$ approximately the valley, $0\mathrm{.}6is$ the

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

$?$ xdot: the velocity $of$ the robot $(this$ can $go$ from $-0\mathrm{.}07to0\mathrm{.}07)$

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.$-\mathrm{.}5,$ one for $>\mathrm{.}5-\mathrm{.}08,$ one for $>\mathrm{.}08$