Yoheita Onishi yoheitaonishi
yoheitaonishi
/ reward_to_go.py
Created
November 16, 2018 19:12
This file contains 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
| import tensorflow as tf | |
| import numpy as np | |
| import gym | |
| from gym.spaces import Discrete, Box | |
| def mlp(x, sizes, activation=tf.tanh, output_activation=None): | |
| # Build a feedforward neural network. | |
| for size in sizes[:-1]: | |
| x = tf.layers.dense(x, units=size, activation=activation) | |
| return tf.layers.dense(x, units=sizes[-1], activation=output_activation) |
yoheitaonishi
/ 1_simple_pg.py
Created
November 15, 2018 19:15
This file contains 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
| import tensorflow as tf | |
| import numpy as np | |
| import gym | |
| from gym.spaces import Discrete, Box | |
| def mlp(x, sizes, activation=tf.tanh, output_activation=None): | |
| # Build a feedforward neural network. | |
| for size in sizes[:-1]: | |
| x = tf.layers.dense(x, units=size, activation=activation) | |
| return tf.layers.dense(x, units=sizes[-1], activation=output_activation) |
yoheitaonishi
/ Deep-Recurrent-Q-Network.ipynb
Last active
November 5, 2018 13:56
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
yoheitaonishi
/ Double-Dueling-DQN.ipynb
Last active
November 3, 2018 12:53
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
yoheitaonishi
/ Vanilla-Policy.ipynb
Last active
November 3, 2018 12:54
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.