Reinforcement learning

• This is where I write various RL algorithms in python.
• Will keep updating as I keep learning more.
• Will try to document as well as I can

Currently my only source for learning is "Reinforcement Learning: An Introduction book by Andrew Barto and Richard S. Sutton"

Progress

• random walk from Sutton and Barto's book
• Model dependent
  • Value iteration
  • Policy iteration
• Model independent
  • Q-learning (TD0)
  • SARSA (TD0)
  • Expected SARSA (TD0)
  • TD-lambda methods
  • k-step SARSA

TODO

• Gauss-Seidel Value iteration
• Asynchronous Value iteration
• More from here