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

greeness

import numpy
import math

# LSH signature generation using random projection
def get_signature(user_vector, rand_proj): 
    res = 0
    for p in (rand_proj):
        res = res << 1
        val = numpy.dot(p, user_vector)
        if val >= 0: