Assignment

The goal of this assignment is to implement one of the Function Approximation or Policy Gradient methods on Taxi$-$v$3$ enviroment at openai gym framework. You are expected to use only linear function for your Value or Policy functions.

Your task in this enviroment is to pick up the passenger at one location and drop him off in another, located at possible $4$ locations $($labeled by different letters$).$ You are expected to pick him up at Y and drop him at G$.$ You receive $+20$ points for a successful dropoff, and lose $1$ point for every timestep it takes. There is also a $10$ point penalty for illegal pick$-$up and drop$-$off actions.

Note that dynamics of the model are assumed to be unknown.

You can access the enviroment information from enviroment variable.

env.env.nS : number of states

env.env.nA : number of possible actions

There are four designated pick$-$up and dropoff locations $($Red$,$ Green, Yellow and Blue$)$ in the $55$ grid world. The taxi starts off at a random square and the passenger at one of the designated locations.

The goal is move the taxi to the passenger's location, pick up the passenger, move to the passenger's desired destination, and drop off the passenger. Once the passenger is dropped off, the episode ends.

The player receives positive rewards for successfully dropping$-$off the passenger at the correct location. Negative rewards for incorrect attempts to pick$-$up$/$drop$-$off passenger and for each step where another reward is not received.

What to submit:

Your source file, Report explaning method you have used and your implementation.

$5-10$ min video recording that presents your workkk

$$

$$