Markov-Decision-Processes

Assignment 3, COL333 Principles of Artificial Intelligence, Sem I 2021-22

This assignment has 2 parts:

1. Value Iteration and Policy Iteration
2. Q-Learning and SARSA Learning

Instructions to run any part:

1. Modify the name == "main" block at the end of A3.py to call the function for the required part. The functions that can be called are partA_2a(), partA_2b(), partA_2c(), partA_3b(1), partA_3b(2), partB_2(), partB_3(), partB_4() and partB_5().

2. Run the file using the command: python A3.py

Required Packages:

1. numpy==1.19.2
2. matplotlib==3.3.4

Tested with python version 3.6.