alex-decastro decastro-alex

## pg-pong.py
""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym

# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward

## keybase.md

      
        
          
            
              
              1 file
            
          
          
            
              
              0 forks
            
          
          
            
              
              0 comments
            
          
          
            
              
              0 stars
            
          
        
        
          
              
          
          
            
                decastro-alex
                / keybase.md
            
            
              Created
              September 21, 2017 08:58
            
          
        
      
        
  
      
    Keybase proof

I hereby claim:

I am decastro-alex on github.
I am alex_decastro (https://keybase.io/alex_decastro) on keybase.
I have a public key ASBLi2xgS0cjfMF1ySDmWOqN5aQLsFTIbZg4ytR2YsyeYQo

To claim this, I am signing this object:
	""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
	import numpy as np
	import cPickle as pickle
	import gym

	# hyperparameters
	H = 200 # number of hidden layer neurons
	batch_size = 10 # every how many episodes to do a param update?
	learning_rate = 1e-4
	gamma = 0.99 # discount factor for reward