Reinforcement Learning

This repository implements reinforcement learning algorithms for AI agents, focusing on decision-making strategies in game environments.

Features:

• Value Iteration (VI): A dynamic programming algorithm for computing the optimal policy and value function.
• Policy Iteration (PI): Another dynamic programming method for computing the optimal policy through iterative policy evaluation and improvement.
• Q-learning: A popular model-free reinforcement learning algorithm to learn the value of actions.

For more details, please refer to the provided documentation.

---

Contributor: Sepide Bahrami

---