Reinforcement Learning Assignments

Welcome to the repository for Reinforcement Learning assignments completed during my Master's program at the University of Tehran.

Overview

This repository contains the code and related materials for the computer assignments completed as part of the Reinforcement Learning course. The assignments cover various topics and techniques in reinforcement learning, providing hands-on experience in implementing algorithms and solving problems in this field.

Assignments

Assignment 1: Introduction to Reinforcement Learning - Description: Basic reinforcement learning concepts, such as value iteration, policy iteration, and dynamic programming. - Files: CA1/

Assignment 2: Markov Decision Processes (MDPs) - Description: Understanding Markov decision processes and solving MDP problems using value iteration and policy iteration. - Files: CA2-1/ , CA2-2/

Assignment 3: Model-Free Prediction - Description: Implementing model-free prediction methods, including Monte Carlo prediction and temporal difference learning (TD(0)). - Files: CA3/

Assignment 4: Model-Free Control - Description: Implementing model-free control methods, such as SARSA (State-Action-Reward-State-Action) and Q-learning. - Files: CA4/

Assignment 5: Deep Reinforcement Learning - Description: Introduction to deep reinforcement learning, including deep Q-networks (DQN) and policy gradient methods. - Files: CA5/

Getting Started

To get started with the assignments, follow these steps:

1. Clone the repository to your local machine:

   git clone https://github.com/Mahsatajik/Reinforcement-Learning.git

2. Navigate to the specific assignment directory you want to work on:

   cd CAX/

3. Follow the instructions provided in the assignment's code files to complete the tasks.

Requirements

Each assignment may have specific requirements and dependencies. Make sure to read the instructions carefully and install any necessary libraries or packages before running the code.

Notes

• Feel free to explore additional resources and extend the assignments as you see fit.
• If you encounter any issues or have questions, don't hesitate to reach out for assistance.