Skip to content

Instantly share code, notes, and snippets.

Avatar

Neal McBurnett nealmcb

View GitHub Profile
@nealmcb
nealmcb / pg-pong.py
Last active Jun 21, 2016 — forked from karpathy/pg-pong.py
Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels
View pg-pong.py
"""pg-pong.py: 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 https://gist.github.com/karpathy/a4166c7fe253700972fcbc77e4ea32c5
to print timestamped self-contained progress rows in TSV format (filter
for just lines containing 'episode').
For background, see http://karpathy.github.io/2016/05/31/rl/
View pack.rb
# just playing
def self.pkg(platform, opt)
# short time solution <start>
extension = case platform
when "win32" then
"exe"
when "linux" then
"run"
when "osx" then
"dmg"
You can’t perform that action at this time.