Data Skeptic

Goodhart's Law in Reinforcement Learning

Mar 5, 2021

37:11

Creator website

Highlights

AI Chapters

Episode notes

Reactor Learning

02:16

Deepralan

05:19

Reinforcement Learning Does Work

01:40

Introduction

4min

Reinforcement Learning Does Work

2min

The Canonical Success Examples of Arel Are in Computer Games

2min

Deepralan

5min

A Simple Causal Diagram of a Dog's Behavior

1min

How Do You Know if It's Raining?

2min

Using Python to Develop Deep Learning Argarithms

1min

Linkdon Jobs - How to Find the Right Candidate

3min

What's the Difference Between on Policy Learning and Off Policy Learning?

3min

10.

The Cobra Effect - An Apocryphal Story

5min

11.

The Ladd of Causation in Machine Learning

3min

12.

Machine Learning Is Not Just for Social Media and Content Suggestion

2min

13.

Reactor Learning

2min

14.

Data Sceptic Con Sensus

56sec

Hal Ashton, a PhD student from the University College of London, joins us today to discuss a recent work Causal Campbell-Goodhart’s law and Reinforcement Learning.

"Only buy honey from a local producer." - Hal Ashton

Works Mentioned:

“Causal Campbell-Goodhart’s law and Reinforcement Learning”by Hal AshtonBook “The Book of Why”by Judea PearlPaper

Thanks to our sponsor!

When your business is ready to make that next hire, find the right person with LinkedIn Jobs. Just visit LinkedIn.com/DATASKEPTIC to post a job for free! Terms and conditions apply