[Illinois]: Perturbative Reinforcement Learning Using Directed Drift

By AbderRahman N Sobh1, Jessica S Johnson1, NanoBio Node1

1. University of Illinois at Urbana-Champaign

This tool trains two-layered networks of sigmoidal units to associate patterns using a real-valued adaptation of the directed drift algorithm.

Launch Tool

You must login before you can run this tool.

Version 1.0d - published on 06 Aug 2014

doi:10.4231/D39P2W68W cite this

Open source: license | download

View All Supporting Documents

Usage

World usage

Location of all "[Illinois]: Perturbative Reinforcement Learning Using Directed Drift" Users Since Its Posting

Simulation Users

2

1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2

Users By Organization Type
Type Users
Educational - University 1 (50%)
Unidentified 1 (50%)
Users by Country of Residence
Country Users
us UNITED STATES 1 (100%)

Simulation Runs

4

1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 4 4 4 4 4 4 4
Overview
Average Total
Wall Clock Time 3.8 minutes 7.6 minutes
CPU time 1.02 seconds 2.04 seconds
Interaction Time 20.2 seconds 40.41 seconds