A2C

2000년 도입 · 논문 82편에서 사용

A2C, or Advantage Actor Critic, is a synchronous version of the A3C policy gradient method. As an alternative to the asynchronous implementation of A3C, A2C is a synchronous, deterministic implementation that waits for each actor to finish its segment of experience before updating, averaging over all of the actors. This more effectively uses GPUs due to larger batch sizes. Image Credit: OpenAI Baselines

출처: Asynchronous Methods for Deep Reinforcement Learning

소개 논문: Asynchronous Methods for Deep Reinforcement Learning