Reinforcement Learning

This repository contains practical projects in reinforcement learning. Key concepts like Multi-Armed Bandits, FMDPs, and both Model-Based and Model-Free algorithms (DP, MC, TD) are implemented. The goal is to gain hands-on experience and a deeper understanding of various RL methods.

• 1. Multi-Armed bandit (MAB)
• 2. Finite markov decision processes (FMDP)
• 3. Dynamic programming (DP) (Model-Based)
• 4. Monte carlo (MC) (Model-Free)
• 5. Temporal difference (TD) (Model-Free)