Software Open Access

Framework for Deep Reinforcement Learning with GPU-CPU Multiprocessing

Ivan Sosin; Oleg Svidchenko; Aleksandra Malysheva; Daniel Kudenko; Aleksei Shpilman


Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Ivan Sosin</dc:creator>
  <dc:creator>Oleg Svidchenko</dc:creator>
  <dc:creator>Aleksandra Malysheva</dc:creator>
  <dc:creator>Daniel Kudenko</dc:creator>
  <dc:creator>Aleksei Shpilman</dc:creator>
  <dc:date>2018-12-04</dc:date>
  <dc:description>One of the main challenges faced in Deep Reinforcement Learning is that running simulations may be CPU-heavy, while the optimal computing device for training neural networks is a GPU. One way to overcome this problem is building a custom machine with GPU to CPU proportions that avoid bottlenecking one or the other. Another is to have the GPU machine work together with the CPU machine and/or launching one or both via cloud computing service. We have designed a framework for such a tandem interaction.

Authors: Ivan Sosin, Oleg Svidchenko, Aleksandra Malysheva, Daniel Kudenko, Aleksei Shpilman.</dc:description>
  <dc:identifier>https://zenodo.org/record/1938263</dc:identifier>
  <dc:identifier>10.5281/zenodo.1938263</dc:identifier>
  <dc:identifier>oai:zenodo.org:1938263</dc:identifier>
  <dc:relation>url:https://github.com/iasawseen/MultiServerRL/tree/v1.0</dc:relation>
  <dc:relation>doi:10.5281/zenodo.1938262</dc:relation>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:title>Framework for Deep Reinforcement Learning with GPU-CPU Multiprocessing</dc:title>
  <dc:type>info:eu-repo/semantics/other</dc:type>
  <dc:type>software</dc:type>
</oai_dc:dc>
145
9
views
downloads
All versions This version
Views 145145
Downloads 99
Data volume 181.7 kB181.7 kB
Unique views 125125
Unique downloads 99

Share

Cite as