Listen Top Shows Blog

Give that model a treat! : Reinforcement learning explained

Give that model a treat! : Reinforcement learning explained

Update: 2020-07-22

Share

Description

Switching gears, we focus on how Yannick’s been training his model using reinforcement learning. He explains the differences from David’s supervised learning approach. We find out how his system performs against a player that makes random tic-tac-toe moves.

Resources:

Deep Learning for JavaScript book

Playing Atari with Deep Reinforcement Learning

Two Minute Papers episode on Atari DQN

For more information about the show, check out pair.withgoogle.com/thehardway/.

You can reach out to the hosts on Twitter: @dweinberger and @tafsiri.

Comments

In Channel

Introducing Tic-Tac-Toe the Hard Way

Introducing Tic-Tac-Toe the Hard Way

2020-07-2102:09

Howdy, and the myth of “pouring in data”

Howdy, and the myth of “pouring in data”

2020-07-2122:01

What does a tic-tac-toe board look like to machine learning?

What does a tic-tac-toe board look like to machine learning?

2020-07-2223:26

From tic-tac-toe moves to ML model

From tic-tac-toe moves to ML model

2020-07-2221:37

Beating random: What it means to have trained a model

Beating random: What it means to have trained a model

2020-07-2217:14

Give that model a treat! : Reinforcement learning explained

Give that model a treat! : Reinforcement learning explained

2020-07-2226:04

Head to Head: the Big ML Smackdown!

Head to Head: the Big ML Smackdown!

2020-07-2225:19

Enter tic-tac-two

Enter tic-tac-two

2020-07-2221:20

Head to Head: The Even Bigger ML Smackdown!

Head to Head: The Even Bigger ML Smackdown!

2020-07-2224:26

Lessons learned

Lessons learned

2020-07-2233:01

00:00

00:00

x

Give that model a treat! : Reinforcement learning explained

Give that model a treat! : Reinforcement learning explained

People + AI Research