[Question] Does a2c support distributed processing?

ikostrikov / pytorch-a3c

PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".

MIT License

1.23k stars 279 forks source link

[Question] Does a2c support distributed processing? #67

Open QiXuanWang opened 5 years ago

QiXuanWang commented 5 years ago

As you mentioned that A2C is strongly suggested except for specific reason. So if I need to run it in distributed processing, (actually only for collecting data in real time), would A3C a better choice than A2C?