Skip to content

Latest commit

 

History

History
15 lines (12 loc) · 582 Bytes

README.md

File metadata and controls

15 lines (12 loc) · 582 Bytes
Raw

Simple-Double-Q-Learning

Simple implementation of double Q-Learning based on MorvanZhou's RL code

Double Q-Learning paper:

https://papers.nips.cc/paper/2010/file/091d584fced301b442654dd8c23b3fc9-Paper.pdf

MovanZhou's code:

https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/blob/master/contents/1_command_line_reinforcement_learning/treasure_on_right.py

Details

python double_q_learning.py
  • You can adjust FRESH_TIME and SHOW_TIME to slow down the game process
  • You can uncommon the print line to see how Q-table is iterated