Status: (Final)
Authors: [email protected]
Reviewers: dfawley@, menghanl@, yuxuanli@, psrini@
Last Updated: 2018-02-25
mmukhi MakMukhi
MakMukhi
/ agentpong_actionvalue.py
Created
July 17, 2017 00:27
NeuralNet to learn and play Atari pong based on Q-learning.
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
| import numpy as np | |
| import _pickle as pickle | |
| import gym | |
| # Fully connected NeuralNet with minimum two layers. | |
| # This is a simple implementation with no bias parameters. | |
| # To work with RL this neural net is such that it feedforwards | |
| # for only example at a time but backprops a batch. | |
| class NeuralNet: |