Skip to content

Instantly share code, notes, and snippets.


Neal McBurnett nealmcb

View GitHub Profile
nealmcb /
Last active Jun 21, 2016 — forked from karpathy/
Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels
""" Trains an agent with (stochastic) Policy Gradients on Pong.
Uses OpenAI Gym.
Saves model every 100 episodes. Resume by setting resume = True
Set render = True to watch the action.
Modified from
to print timestamped self-contained progress rows in TSV format (filter
for just lines containing 'episode').
For background, see
View pack.rb
# just playing
def self.pkg(platform, opt)
# short time solution <start>
extension = case platform
when "win32" then
when "linux" then
when "osx" then
You can’t perform that action at this time.