Skip to content

Latest commit

 

History

History
5 lines (4 loc) · 231 Bytes

README.md

File metadata and controls

5 lines (4 loc) · 231 Bytes

My take on playing atari using reinforcement learning: https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf

Work still in progress (it's bugged). My goal is to implement version with double q-learning and prioritized experience replay.