David Whitney dwhit
dwhit
/ pg-pong.py
Last active
June 7, 2016 18:43
— forked from karpathy/pg-pong.py
Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels
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
| """ Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. | |
| I've edited the file so that the weights of different episodes are saved. They are | |
| saved in the format: | |
| save-<episode-number>--<running_reward>.p | |
| This way its easy to see what epoch had the most effective weights. | |
| Also, I've made the pickle file store the episode number, and running reward so |