Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU

Abstract

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 .

Cited by in corpus (5)

• A Survey and Critique of Multiagent Deep Reinforcement Learning
• Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox
• Operationally meaningful representations of physical systems in neural networks
• Exploration-efficient Deep Reinforcement Learning with Demonstration Guidance for Robot Control
• Boosting Deep Reinforcement Learning with Semantic Knowledge for Robotic Manipulators