You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
An implementation of the actor-critic famous algorithm in a distributed way. Based on the following paper: Asynchronous Methods for Deep Reinforcement Learning
Comparsion over optimizers and types of network architectures.
Prerequisites
gym~=0.18.0
numpy~=1.18.1
matplotlib~=3.2.2
About
An implementation of the actor-critic famous algorithm in a distributed way. Based on the following paper: Asynchronous Methods for Deep Reinforcement Learning