Software Open Access
Framework for Deep Reinforcement Learning with GPU-CPU Multiprocessing
Ivan Sosin; Oleg Svidchenko; Aleksandra Malysheva; Daniel Kudenko; Aleksei Shpilman
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.
| Name | Size | |
|---|---|---|
|
iasawseen/MultiServerRL-v1.0.zip
md5:569c93638c7a3485b8c74839b7f16af0 |
20.2 kB | Download |
| All versions | This version | |
|---|---|---|
| Views | 92 | 92 |
| Downloads | 5 | 5 |
| Data volume | 100.9 kB | 100.9 kB |
| Unique views | 72 | 72 |
| Unique downloads | 5 | 5 |
- Publication date:
- December 4, 2018
- DOI:
-
- Related identifiers:
- Supplement to:
https://github.com/iasawseen/MultiServerRL/tree/v1.0 - License (for files):
- Other (Open)