Skip to content

Instantly share code, notes, and snippets.

View TheMikeyR's full-sized avatar

Mike R TheMikeyR

  • Aalborg, Denmark
View GitHub Profile
@karpathy
karpathy / pg-pong.py
Created May 30, 2016 22:50
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. """
import numpy as np
import cPickle as pickle
import gym
# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward
@justbuchanan
justbuchanan / readme.md
Last active March 1, 2021 17:21
Show icons for open programs in i3's status bar. See a demo here: http://gfycat.com/AfraidAmusingCoyote