Simple Reinforcement Learning with Tensorflow Part 8: Asynchronous Actor-Critic Agents (A3C)
Arthur Juliani
3.5K80

Thank you for this awesome series. So, I’m trying to get A3C to work in the Atari gym domain. I was able to have it successfully work with Pong because it learns pretty fast. However, I’m trying it now with Breakout. The problem is that it takes a while to learn Breakout and training seems to slow down quite dramatically that it almost seems like it hanging up, but it’s not. I wonder which part of the code is causing this or has anyone experience this?

Like what you read? Give Gabriel de la Cruz a round of applause.

From a quick cheer to a standing ovation, clap to show how much you enjoyed this story.