rlstudy
A2C demo
Advantage Actor-Critic
sample TensorFlow implementation of the Advantage Actor-Critic model for Atari games.
As an alternative to the asynchronous implementation, researchers found you can write asynchronous, deterministic implementation that waits for each actor to finish its segment of experience before performing an update, averaging over all of the actors. One advantage of this method is that it can more effectively use of GPUs, which perform best with large batch sizes. This algorithm is naturally called A2C, short for advantage actor-critic.
The gym environment wrappers used are from Open AI baseline