A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf
.
Distributed Deep Reinforcement Learning: Learn How to Play Atari Games in 21 minutes
[chapter]
2018
Lecture Notes in Computer Science
We present a study in Distributed Deep Reinforcement Learning (DDRL) focused on scalability of a state-of-the-art Deep Reinforcement Learning algorithm known as Batch Asynchronous Advantage Actor-Critic (BA3C). We show that using the Adam optimization algorithm with a batch size of up to 2048 is a viable choice for carrying out large scale machine learning computations. This, combined with careful reexamination of the optimizer's hyperparameters, using synchronous training on the node level
doi:10.1007/978-3-319-92040-5_19
fatcat:armgndw6u5afvcpg64rl2kyqk4