Skip to content

Latest commit

 

History

History
16 lines (12 loc) · 429 Bytes

README.md

File metadata and controls

16 lines (12 loc) · 429 Bytes

Reinforcement-learning

  • homework assignments and some algorithms associated with my reinforcement learning class
  1. Monte-carlo, temporal difference:
  • MC-nonstationary
  • MC-incremental
  • TD(0)
  • TD-forward(0.5)
  • TD-backward(0.5)
  1. Sarsa (state-action-reward-state-action), Q-learning: (on Windy Gridworld with and w/o King’s Moves respectively, Reinforcement Learning textbook)
  • Sarsa (done)
  • Q-learning