robinheghan

module Main where

import Signal


type alias Message =
    { operation : String
    , message : String
    }

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

ilblackdragon

import logging

import numpy as np
import tensorflow as tf
from tensorflow.contrib import layers


GO_TOKEN = 0
END_TOKEN = 1
UNK_TOKEN = 2