Hindsight Experience Relay: The algorithm that lets AI learn from its mistakes
Software

Hindsight Experience Relay: The algorithm that lets AI learn from its mistakes

OpenAI has developed an algorithm that can learn from its mistakes. How will this pave the way for AGI?

By admin / August 28, 2019

The hindsight experience relay (HER) was developed in 2018 by OpenAI and was designed so that algorithms can learn every time it completes a task. While it is similar to the algorithm behind AphaZero, HER was designed to achieve multiple goals.

The attached article was written early this 2019 by Or Rivlin. It explains how HER works, and the implications to machine learning.

Read Original Article

Read Online

Click the button below if you wish to read the article on the website where it was originally published.

Visit Source

Read Offline

Click button below if you wish to read the original article offline.

Download PDF

Oh hi there 👋
It’s nice to meet you.

Sign up to receive awesome content in your inbox, every week.

Your e-mail address is only used to send you our newsletter and information about the activities of Fully Human.

You may also like

Leave a Reply

Your email address will not be published. Required fields are marked *