Viet-Anh on Software Logo

What is: ACTKR?

SourceScalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

ACKTR, or Actor Critic with Kronecker-factored Trust Region, is an actor-critic method for reinforcement learning that applies trust region optimization using a recently proposed Kronecker-factored approximation to the curvature. The method extends the framework of natural policy gradient and optimizes both the actor and the critic using Kronecker-factored approximate curvature (K-FAC) with trust region.