Reinforcement Learning Exercises

This repository contains step-by-step implementations of key reinforcement learning algorithms.

Purpose

• To practice and understand RL algorithms from scratch.
• To apply them in OpenAI Gym environments.
• To transition from model-based planning (like value/policy iteration) to model-free learning (like Q-learning, SARSA, DQN).

Effects

• Develop intuition for dynamic programming in RL.
• Learn to implement and debug algorithms from first principles.
• Build a clean foundation for real-world reinforcement learning problems.