Bart Keulen BartKeulen
BartKeulen
/ log.txt
Last active
May 12, 2017 23:17
Error log installing rllab. System info: Distributor ID: Ubuntu, Description: Ubuntu 16.04.2 LTS, Release: 16.04, Codename: xenial. Python info: Python 3.5.2 |Continuum Analytics, Inc.| (default, Jul 2 2016, 17:53:06) [GCC 4.4.7 20120313 (Red Hat 4.4.7-1)] on linux
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
| ./scripts/setup_linux.sh | |
| Installing system dependencies | |
| You will probably be asked for your sudo password. | |
| Get:1 file:/var/cuda-repo-8-0-local InRelease | |
| Ign:1 file:/var/cuda-repo-8-0-local InRelease | |
| Get:2 file:/var/cuda-repo-8-0-local Release [574 B] | |
| Get:2 file:/var/cuda-repo-8-0-local Release [574 B] | |
| Ign:4 http://desktop-download.mendeley.com/download/apt stable InRelease | |
| Hit:5 http://desktop-download.mendeley.com/download/apt stable Release | |
| Hit:6 http://us.archive.ubuntu.com/ubuntu xenial InRelease |
BartKeulen
/ GradientTest.java
Last active
April 4, 2017 22:35
Deeplearning4j version: 0.8.0; OS: Ubuntu 16.04.1 LTS; Java version: 1.8.0_121
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
| public class GradientTest { | |
| private static final Logger logger = LoggerFactory.getLogger(GradientTest.class); | |
| public static void main(String[] args) { | |
| //Create the model | |
| int nIn = 2; | |
| int nOut = 1; | |
| Nd4j.getRandom().setSeed(12345); |
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
| import java.awt.*; | |
| import javax.swing.JFrame; | |
| import javax.swing.JPanel; | |
| import smile.plot.*; | |
| /** | |
| * |
BartKeulen
/ features.py
Created
February 15, 2017 15:57
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
| import numpy as np | |
| class TileCoding(object): | |
| def __init__(self, func_approx_settings): | |
| self.num_tilings = func_approx_settings['num_tilings'] | |
| assert(self.num_tilings % 2 == 0) | |
| self.state_dim = func_approx_settings['state_dim'] | |
| self.bound_low = func_approx_settings['bound_low'] |
BartKeulen
/ actor.py
Last active
March 14, 2017 08:47
DDPG algorithm according to https://arxiv.org/abs/1509.02971. Implementation from https://pemami4911.github.io/blog/2016/08/21/ddpg-rl.html. Added Ornstein-Uhlenbeck process noise and exponential and -tanh noise decay.
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
| """ | |
| Data structure for implementing actor network for DDPG algorithm | |
| Algorithm and hyperparameter details can be found here: | |
| http://arxiv.org/pdf/1509.02971v2.pdf | |
| Original author: Patrick Emami | |
| Author: Bart Keulen | |
| """ |