sritee
/ PG.py
Last active
June 7, 2018 19:54
— forked from MikeOuimet/PG.py
Vanilla policy gradient with tensorflow
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #improved GIST of https://gist.github.com/MikeOuimet/f50904374651c9c15f236aef3109d57 | |
| #allowed backwards compatability by refactoring code involving tf.diag gradients | |
| 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) |