Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU

Code

• github.com/NVlabs/GA3C
  OfficialIn papertf★ 0
• github.com/nicoladainese96/SC2-RL
  pytorch★ 6
• github.com/Sheepsody/Batched-Impala-PyTorch
  pytorch★ 0

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 .

Tasks

Reproductions