hughperkins

""" 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

hughperkins

/* Minimal declarations for CUDA support.  Testing purposes only. */

#define __constant__ __attribute__((constant))
#define __device__ __attribute__((device))
#define __global__ extern "C" __attribute__((global))
#define __host__ __attribute__((host))
#define __shared__ __attribute__((shared))
#define __launch_bounds__(...) __attribute__((launch_bounds(__VA_ARGS__)))
#define __forceinline__ __attribute__((always_inline))

hughperkins

# Note – this is not a bash script (some of the steps require reboot)
# I named it .sh just so Github does correct syntax highlighting.
#
# This is also available as an AMI in us-east-1 (virginia): ami-cf5028a5
#
# The CUDA part is mostly based on this excellent blog post:
# http://tleyden.github.io/blog/2014/10/25/cuda-6-dot-5-on-aws-gpu-instance-running-ubuntu-14-dot-04/

# Install various packages
sudo apt-get update