Index (Reinforcement Learning)

• Introduction

Model free methods

• Imitation Learning
• Policy Gradients
• Actor-Critic (todo)
• Q-Learning (todo)

Model based methods

• Policy Iterations (todo)
• Value Iterations (todo)

Acknowledgements - The structure of the lecture notes are loosely based on CS285 course from UC Berkeley by Prof. Sergey Levine and E0277 course from Indian Institute of Science (IISc) by Prof Shalabh Bhatnagar.