Skip to content

Instantly share code, notes, and snippets.

View MikeOuimet's full-sized avatar

Mike MikeOuimet

  • San Diego, CA
View GitHub Profile
@MikeOuimet
MikeOuimet / PG.py
Created September 25, 2016 20:09
Vanilla policy gradient with tensorflow
import numpy as np
import gym
import tensorflow as tf
import matplotlib.pyplot as plt
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):