Asynchronous Methods For Deep Reinforcement Learning

A arXiv:1611.01578v2 [cs.LG] 15 Feb 2017

asynchronous parameter updates in order to speed up the learning process of the controller (Dean et al., 2012). We use a parameter-server scheme where we have a parameter server of Sshards, that store the shared parameters for Kcontroller replicas. Each controller replica samples mdifferent child architectures that are trained in parallel.

  Learning, Asynchronous

Python code for Artificial Intelligence: Foundations of ...

1 Python code for Artificial Intelligence: Foundations of Computational Agents David L. Poole and Alan K. Mackworth Version 0.9.0 of July 2, 2021.