piyush-jena / reinforcement-learning

This repository contains implementations of popular Reinforcement Learning algorithms.

Reinforcement Learning

This repository contains implementations of popular Reinforcement Learning algorithms in simple settings.

Content

1. Policy Iteration in OpenAI Gym (Frozen Lake)
2. Q-Learning and SARSA in OpenAI Gym (Frozen Lake)
3. Deep Q-Network (DQN) in OpenAI Gym (CartPole)
4. Alpha Beta Pruning for MNK Game
5. Monte Carlo Tree Search for MNK Game

Running Instructions

1. For the first 3 parts the ipynb are standalone and fully working.
2. For MNK Game, poetry file and running instructions are given inside.

License

MIT