PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".
Why do you think that https://github.com/thu-ml/tianshou is a good alternative to pytorch-a3c
PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".
Why do you think that https://github.com/thu-ml/tianshou is a good alternative to pytorch-a3c