1. [Publications](/publications)
2. Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU
 
 # Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU

  ![Publication image](/sites/default/files/styles/wide/public/default_images/default.jpeg?itok=qUFsuJCP "Publication image")

 We introduce a hybrid CPU/GPU version of the Asynchronous Advantage Actor-Critic (A3C) algorithm, currently the state-of-the art method in reinforcement learning for various gaming tasks. We analyze its computational traits and concentrate on aspects critical to leveraging the GPU's computational power. We introduce a system of queues and a dynamic scheduling strategy, potentially helpful for other asynchronous algorithms as well. Our hybrid CPU/GPU version of A3C, based on TensorFlow, achieves a significant speed up compared to a CPU implementation; we make it publicly available to other researchers at <https://github.com/NVlabs/GA3C>.



 ## Authors



Mohammad Babaeizadeh (University of Illinois at Urbana-Champaign)

[Iuri Frosio](/person/iuri-frosio)

[Stephen Tyree](/person/stephen-tyree)

[Jason Clemons](/person/jason-clemons)

[Jan Kautz](/person/jan-kautz)

 

 

 ## Publication Date



Friday, November 18, 2016

 

 ## Published in



[arXiv](https://arxiv.org/abs/1611.06256)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)