This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package org.papasofokli | |
import scala.util.parsing.combinator.JavaTokenParsers | |
/** | |
* <b-expression>::= <b-term> [<orop> <b-term>]* | |
* <b-term> ::= <not-factor> [AND <not-factor>]* | |
* <not-factor> ::= [NOT] <b-factor> | |
* <b-factor> ::= <b-literal> | <b-variable> | (<b-expression>) | |
*/ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
A deep neural network with or w/o dropout in one file. | |
License: Do What The Fuck You Want to Public License http://www.wtfpl.net/ | |
""" | |
import numpy, theano, sys, math | |
from theano import tensor as T | |
from theano import shared | |
from theano.tensor.shared_randomstreams import RandomStreams |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
# You must accept the Oracle JDK License Update | |
# https://www.oracle.com/java/technologies/javase-downloads.html | |
# usage: get_oracle_jdk_x64.sh <jdk_version> <platform> <ext> | |
# jdk_version: 14 | |
# platform: linux or osx or windows | |
# ext: rpm or dmg or tar.gz or exec | |
jdk_version=${1:-14} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" 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 |