Open in app
Arthur Juliani
11.9K Followers
About

Sign in

11.9K Followers
About
Open in app
Arthur Juliani

Arthur Juliani

Apr 8, 2017·1 min read

Hi MT,

To answer your two questions:

  1. The original A3C paper: https://arxiv.org/abs/1602.01783 contains an explanation of value and entropy regularization.
  2. Yep. It is just set to `1` in this case.

Hope that helps!

Arthur Juliani

PhD. Interests include Deep (Reinforcement) Learning, Computational Neuroscience, and Phenomenology.

Arthur,
1

MT

More from Arthur Juliani

PhD. Interests include Deep (Reinforcement) Learning, Computational Neuroscience, and Phenomenology.

More From Medium

Thoughts on “Symbolic Behavior in Artificial Intelligence”

Arthur Juliani

Maximum Entropy Policies in Reinforcement Learning & Everyday Life

Arthur Juliani

On “solving” Montezuma’s Revenge

Arthur Juliani

Thoughts on “Things Hidden Since the Foundation of the World”

Arthur Juliani

Japanese Role Playing Games as a Meta Reinforcement Learning Benchmark

Arthur Juliani

A Man In His 30s Explains To Me What’s Wrong With Women In Their 30s

Hannah Furst in Slackjaw

My M1 Macbook Air is DEAD.

Tan Han Wei in CodeX

How I Earn $8K+ Per Month While Only Working 15 Hours Per Week

Zulie Rane in The Startup

About

Help

Legal

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store