| """ Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """ | |
| import numpy as np | |
| import cPickle as pickle | |
| import gym | |
| from chainer import cuda | |
| import cupy as cp | |
| import time, threading | |
| #backend |
| """ 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 |
This document will walk you through compiling your own scientific python distribution from source,
without sudo, on a linux machine. The core numpy and scipy libraries will be linked against
Intel MKL for maximum performance.
This procedure has been tested with Rocks Cluster Linux 6.0 (Mamba) and CentOS 6.3.