Reinforcement-Learning

Implemented RL algorithms (by me):

1. Q-learning (Cart-Pole env.)
2. Double Q-learning (Cart-Pole env.)
3. Sarsa (Frozen-Lake env.)
4. Sarsa(λ) (Frozen-Lake env.)
5. Deep Q-Network (DQN) (Cart-Pole env.)
6. REINFORCE (Cart-Pole env.)
7. Advantage Actor-Critic (A2C) (Cart-Pole env.)

Study Resources

Online Courses:

• David Silver's RL Course (UCL, 2015)

Textbooks:

• Reinforcement Learning: Introduction (Richard Sutton & Andrew G. Barto, 2018)

Other Helpful materials/articles:

• Key papers in Deep RL by Open AI
• An Intuitive Explanation of Policy Gradient

Author

Yeskendir Koishekenov @YeskendirK