karpathy

""" 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

laispace

git config --global https.proxy http://127.0.0.1:1080

git config --global https.proxy https://127.0.0.1:1080

git config --global --unset http.proxy

git config --global --unset https.proxy


npm config delete proxy