Name
Title | ||
|---|---|---|
Accelerating Distributed Deep Reinforcement Learning by In-Network Experience Sampling |
Abstract | ||
|---|---|---|
A computing cluster that interconnects multiple compute nodes is used to accelerate distributed reinforcement learning based on DQN (Deep Q-Network). In distributed reinforcement learning, Actor nodes acquire experiences by interacting with a given environment and a Learner node optimizes their DQN model. Since data transfer between Actor and Learner nodes increases depending on the number of Acto... |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/PDP55904.2022.00020 | 2022 30th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP) |
Keywords | DocType | ISSN |
Computational modeling,Reinforcement learning,Ethernet,Data transfer,Servers,Low latency communication,Kernel | Conference | 1066-6192 |
ISBN | Citations | PageRank |
978-1-6654-6958-6 | 0 | 0.34 |
References | Authors | |
0 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Masaki Furukawa | 1 | 0 | 0.68 |
| Hiroki Matsutani | 2 | 0 | 1.35 |