Skip to content

Instantly share code, notes, and snippets.

@d0znpp
Created December 12, 2017 00:43
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 d0znpp/05169a3513cf73a5c2a89c6471e395b6 to your computer and use it in GitHub Desktop.
Save d0znpp/05169a3513cf73a5c2a89c6471e395b6 to your computer and use it in GitHub Desktop.
class Reinforce():
def __init__(self, sess, optimizer, policy_network, max_layers, global_step,
division_rate=100.0,
reg_param=0.001,
discount_factor=0.99,
exploration=0.3):
self.sess = sess
self.optimizer = optimizer
self.policy_network = policy_network
self.division_rate = division_rate
self.reg_param = reg_param
self.discount_factor=discount_factor
self.max_layers = max_layers
self.global_step = global_step
self.reward_buffer = []
self.state_buffer = []
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment