This repository contains my Interactive Learning (Reinforcement Learning) course projects at University of Tehran.
- HW1 : Familiarize with the statistical concepts and beginner tools of Python
- HW2 : Presenting a Multi-Armed Bandit model for a real-world problem
- HW3 : Solving the Frozen Lake problem using Policy Iteration and Value Iteration algorithms
- HW4 : Solving the Taxi-v3 problem using Q-learning, SARSA, n-step Tree Backup, and Monte Carlo algorithms
- HW5 : Solving the Highway problem using Deep RL algorithms such as Policy Gradient and Deep Q-learning