Skip to content

Instantly share code, notes, and snippets.

@AurelianTactics

AurelianTactics/trfl_double_q_learning.py

Created January 1, 2019 18:10
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save AurelianTactics/eb9b41906c875f6b0059f56526027b7d to your computer and use it in GitHub Desktop.
Save AurelianTactics/eb9b41906c875f6b0059f56526027b7d to your computer and use it in GitHub Desktop.
Download ZIP
trfl_double_q_learning.py
Raw
trfl_double_q_learning.py
#TRFL qlearning
#qloss, q_learning = trfl.qlearning(self.output,self.actions_,self.reward,self.discount,self.targetQs_)
#TRFL double qlearing
qloss, q_learning = trfl.double_qlearning(self.output,self.actions_,self.reward,self.discount,self.targetQs_,self.output)
self.loss = tf.reduce_mean(qloss)
self.opt = tf.train.AdamOptimizer(learning_rate).minimize(self.loss)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment