Project details for RLLib Lightweight On or Off Policy Reinforcement Learning Library

Logo RLLib Lightweight On or Off Policy Reinforcement Learning Library 1.0.1

by saminda - October 8, 2013, 22:42:34 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ]

view (14 today), download ( 6 today ), 1 subscription

Description:

RLLib

(C++ Template Library to Learn Behaviors and Represent Learnable Knowledge using On/Off Policy Reinforcement Learning)

RLLib is a lightweight C++ template library that implements incremental, standard, and gradient temporal-difference learning algorithms in Reinforcement Learning. It is a highly optimized library that is designed and written specifically for robotic applications. The implementation of the RLLib library is inspired by the RLPark API, which is a library of temporal-difference learning algorithms written in Java.

Features

  • Off-policy prediction algorithms: GTD(lambda) GQ(lambda)
  • Off-policy control algorithms:
    Greedy-GQ(lambda) Softmax-GQ(lambda) Off-PAC (can be used in on-policy setting)
  • On-policy algorithms: TD(lambda) SARSA(lambda) Expected-SARSA(lambda) Actor-Critic (continuous and discrete actions, discounted, averaged reward settings, etc.)
  • Supervised learning algorithms: Adaline IDBD SemiLinearIDBD Autostep
  • Policies: Random Random50%Bias Greedy Epsilon-greedy Boltzmann Normal Softmax
  • Dot product: An efficient implementation of the dot product for tile coding based feature representations (with culling traces).
  • Benchmarking environments: Mountain Car Mountain Car 3D Swinging Pendulum Helicopter Continuous Grid World
  • Optimization: Optimized for very fast duty cycles (e.g., with culling traces, RLLib has been tested on the Robocup 3D simulator agent, and on the NAO V4 (cognition thread)).
  • Usage: The algorithm usage is very much similar to RLPark, therefore, swift learning curve.
  • Examples: There are a plethora of examples demonstrating on-policy and off-policy control experiments.
  • Visualization: We provide a Qt4 based application to visualize benchmark problems.

Usage

RLLib is a C++ template library. The header files are located in the src directly. You can simply include this directory from your projects, e.g., -I./src, to access the algorithms.

To access the control algorithms:

#include "ControlAlgorithm.h"

To access the predication algorithms:

#include "PredictorAlgorithm"

To access the supervised learning algorithms:

#include "SupervisedAlgorithm.h"

RLLib uses the namespace:

using namespace RLLib

Testing

RLLib provides a flexible testing framework. Follow these steps to quickly write a test case.

  • To access the testing framework: #include "HeaderTest.h"

#include "HeaderTest.h"

RLLIB_TEST(YourTest)

class YourTest Test: public YourTestBase

{

public:

YourTestTest() {}

virtual ~Test() {}

void run();

private:

void testYourMethod();

};

void YourTestBase::testYourMethod() {/* Your test code /}

void YourTestBase::run() { testYourMethod(); }

  • Add YourTest to the test/test.cfg file.

Test Configuration

The test cases are executed using:

./configure
make
./RLLibTest

Documentation

Contact

Saminda Abeyruwan (saminda@cs.miami.edu)

Changes to previous version:

Current release version is v1.0.1.

BibTeX Entry: Download
Corresponding Paper BibTeX Entry: Download
URL: Project Homepage
Supported Operating Systems: Linux, Platform Independent, Windows Under Cygwin
Data Formats: Bin
Tags: Lightweight, Off Policy, On Policy, Reinforcement Learning Library, Standard
Archive: download here

Other available revisons

Version Changelog Date
2.0

Current release version is v2.0.

April 25, 2014, 02:58:32
1.6

Current release version is v1.6.

December 1, 2013, 10:21:06
1.5

Current release version is v1.5.

November 20, 2013, 01:45:44
1.0.2

Current release version is v1.0.2.

October 21, 2013, 05:58:19
1.0.1

Current release version is v1.0.1.

October 8, 2013, 22:42:34
1.0

Initial Announcement on mloss.org.

September 16, 2013, 02:31:21

Comments

No one has posted any comments yet. Perhaps you'd like to be the first?

Leave a comment

You must be logged in to post comments.