Published December 4, 2018
| Version v1.0
Software
Open
Framework for Deep Reinforcement Learning with GPU-CPU Multiprocessing
- 1. JetBrains Research
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.
Files
iasawseen/MultiServerRL-v1.0.zip
Files
(20.2 kB)
Name | Size | Download all |
---|---|---|
md5:569c93638c7a3485b8c74839b7f16af0
|
20.2 kB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/iasawseen/MultiServerRL/tree/v1.0 (URL)