Tic-Tac-Toe the Hard Way Transistor (https://transistor.fm) https://feeds.transistor.fm/tic-tac-toe-the-hard-way A writer and a software engineer from Google's People + AI Research team explore the human choices that shape machine learning systems by building competing tic-tac-toe agents. © 2025 People + AI Research 48949ff6-4f44-5b9f-a5c5-68d75bd22aa1 no Introducing Tic-Tac-Toe the Hard Way en Fri, 09 Feb 2024 15:09:10 -0500 Tue, 02 Dec 2025 16:28:18 -0500 http://pair.withgoogle.com/thehardway/ https://img.transistor.fm/QPOQXD2Zv1iUyQ69H3aaIJ_o9QQ4mW3-RszZfOWpbxk/rs:fill:0:0:1/w:1400/h:1400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9zaG93/LzEyNDcxLzE1OTQ4/NDU3MDctYXJ0d29y/ay5qcGc.jpg Tic-Tac-Toe the Hard Way http://pair.withgoogle.com/thehardway/ serial People + AI Research A writer and a software engineer from Google's People + AI Research team explore the human choices that shape machine learning systems by building competing tic-tac-toe agents. A writer and a software engineer from Google's People + AI Research team explore the human choices that shape machine learning systems by building competing tic-tac-toe agents.. machine learning, ML, AI, human-centered, reinforcement learning, supervised learning, tic-tac-toe, games, Google, tic tac toe Lucas Dixon No No Introducing Tic-Tac-Toe the Hard Way Introducing Tic-Tac-Toe the Hard Way trailer 4caa7322-6e50-45af-856d-5535c0e7973f https://share.transistor.fm/s/1da39dd3 Introducing the podcast where a writer and a software engineer explore the human choices that shape machine learning systems by building competing tic-tac-toe agents. Brought to you by Google's People + AI Research team.

More at: pair.withgoogle.com/thehardway

]]> Introducing the podcast where a writer and a software engineer explore the human choices that shape machine learning systems by building competing tic-tac-toe agents. Brought to you by Google's People + AI Research team.

More at: pair.withgoogle.com/thehardway

]]> Tue, 21 Jul 2020 16:57:00 -0400 People + AI Research People + AI Research 129 Introducing the podcast where a writer and a software engineer explore the human choices that shape machine learning systems by building competing tic-tac-toe agents. Brought to you by Google's People + AI Research team. Introducing the podcast where a writer and a software engineer explore the human choices that shape machine learning systems by building competing tic-tac-toe agents. Brought to you by Google's People + AI Research team. machine learning, ML, AI, human-centered, reinforcement learning, supervised learning, tic-tac-toe, games, Google, tic tac toe No Howdy, and the myth of “pouring in data” 1 1 Howdy, and the myth of “pouring in data” full ff26c8b4-ce61-4f92-90cd-cbc6793f4326 https://share.transistor.fm/s/6768a641 Welcome to the podcast! We’re Yannick and David, a software engineer and a non-technical writer. Over the next 9 episodes we’re going to use two different approaches to build machine learning systems that play two versions of tic-tac-toe. Building a machine learning app requires humans making a lot of decisions. We start by agreeing that David will use a “supervised learning” approach while Yannick will go with “reinforcement learning.”

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


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

]]> Welcome to the podcast! We’re Yannick and David, a software engineer and a non-technical writer. Over the next 9 episodes we’re going to use two different approaches to build machine learning systems that play two versions of tic-tac-toe. Building a machine learning app requires humans making a lot of decisions. We start by agreeing that David will use a “supervised learning” approach while Yannick will go with “reinforcement learning.”

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


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

]]> Tue, 21 Jul 2020 17:05:00 -0400 People + AI Research People + AI Research 1321 David and Yannick get started on their project to build competing machine learning systems that play tic-tac-toe. They discuss the human choices that will shape their systems along the way. David and Yannick get started on their project to build competing machine learning systems that play tic-tac-toe. They discuss the human choices that will shape their systems along the way. machine learning, ML, AI, human-centered, reinforcement learning, supervised learning, tic-tac-toe, games, Google, tic tac toe No What does a tic-tac-toe board look like to machine learning? 2 2 What does a tic-tac-toe board look like to machine learning? full e6e611a1-a894-4dd5-a0f1-99cfbab37428 https://share.transistor.fm/s/eba6db79 How should David represent the data needed to train his machine learning system? What does a tic-tac-toe board “look” like to ML? Should he train it on games or on individual boards? How does this decision affect how and how well the machine will learn to play? Plus, an intro to reinforcement learning, the approach Yannick will be taking.

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


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

]]> How should David represent the data needed to train his machine learning system? What does a tic-tac-toe board “look” like to ML? Should he train it on games or on individual boards? How does this decision affect how and how well the machine will learn to play? Plus, an intro to reinforcement learning, the approach Yannick will be taking.

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


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

]]> Wed, 22 Jul 2020 09:38:00 -0400 People + AI Research People + AI Research 1406 David delves into questions around data and training for his model including: What does a tic-tac-toe board “look” like to ML? Plus, an intro to reinforcement learning, the approach Yannick will be taking. David delves into questions around data and training for his model including: What does a tic-tac-toe board “look” like to ML? Plus, an intro to reinforcement learning, the approach Yannick will be taking. machine learning, ML, AI, human-centered, reinforcement learning, supervised learning, tic-tac-toe, games, Google, tic tac toe No From tic-tac-toe moves to ML model 3 3 From tic-tac-toe moves to ML model full 305a734a-c1a4-4603-aaad-575ed51ea202 https://share.transistor.fm/s/7b0d33a4 Once we have the data we need—thousands of sample games--how do we turn it into something the ML can train itself on? That means understanding how training works, and what a model is.

Resources:
See a definition of one-hot encoding

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


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

]]> Once we have the data we need—thousands of sample games--how do we turn it into something the ML can train itself on? That means understanding how training works, and what a model is.

Resources:
See a definition of one-hot encoding

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


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

]]> Wed, 22 Jul 2020 09:55:00 -0400 People + AI Research People + AI Research 1297 Once we have the data we need—thousands of sample games—how do we turn it into something the ML can train itself on? That means understanding how training works, and what a model is. Once we have the data we need—thousands of sample games—how do we turn it into something the ML can train itself on? That means understanding how training works, and what a model is. machine learning, ML, AI, human-centered, reinforcement learning, supervised learning, tic-tac-toe, games, Google, tic tac toe No Beating random: What it means to have trained a model 4 4 Beating random: What it means to have trained a model full fdccbad0-3827-4ef6-af2a-3d527c7ea96f https://share.transistor.fm/s/65ec8e69 David did it! He trained a machine learning model to play tic-tac-toe! (Well, with lots of help from Yannick.) How did the whole training experience go? How do you tell how training went? How did his model do against a player that makes random tic-tac-toe moves?

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


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

]]> David did it! He trained a machine learning model to play tic-tac-toe! (Well, with lots of help from Yannick.) How did the whole training experience go? How do you tell how training went? How did his model do against a player that makes random tic-tac-toe moves?

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


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

]]> Wed, 22 Jul 2020 11:30:00 -0400 People + AI Research People + AI Research 1034 David did it! He trained a machine learning model to play tic-tac-toe! How did his model do against a player that makes random tic-tac-toe moves? David did it! He trained a machine learning model to play tic-tac-toe! How did his model do against a player that makes random tic-tac-toe moves? machine learning, ML, AI, human-centered, reinforcement learning, supervised learning, tic-tac-toe, games, Google, tic tac toe No Give that model a treat! : Reinforcement learning explained 5 5 Give that model a treat! : Reinforcement learning explained full aca34995-31df-4a19-8f4a-a43e0a5c3e5b https://share.transistor.fm/s/730e69f9 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. 


]]> 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. 


]]> Wed, 22 Jul 2020 11:35:00 -0400 People + AI Research People + AI Research 1564 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. 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 mov machine learning, ML, AI, human-centered, reinforcement learning, supervised learning, tic-tac-toe, games, Google, tic tac toe No Head to Head: the Big ML Smackdown! 6 6 Head to Head: the Big ML Smackdown! full 1521ddac-190c-43f6-949c-017e131b1587 https://share.transistor.fm/s/e2baaaf8 David and Yannick’s tic-tac-toe ML agents face-off against each other in tic-tac-toe!

See the agents play each other!


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


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


]]> David and Yannick’s tic-tac-toe ML agents face-off against each other in tic-tac-toe!

See the agents play each other!


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


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


]]> Wed, 22 Jul 2020 11:45:00 -0400 People + AI Research People + AI Research 1519 David and Yannick’s tic-tac-toe ML agents face-off against each other in tic-tac-toe! David and Yannick’s tic-tac-toe ML agents face-off against each other in tic-tac-toe! machine learning, ML, AI, human-centered, reinforcement learning, supervised learning, tic-tac-toe, games, Google, tic tac toe No Enter tic-tac-two 7 7 Enter tic-tac-two full 5195b4a2-20d1-4a46-a93d-4add4f9ba6b4 https://share.transistor.fm/s/f0d5fead David’s variant of tic-tac-toe that we’re calling tic-tac-two is only slightly different but turns out to be far more complex. This requires rethinking what the ML system will need in order to learn how to play, and  how to represent that data.

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


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

]]> David’s variant of tic-tac-toe that we’re calling tic-tac-two is only slightly different but turns out to be far more complex. This requires rethinking what the ML system will need in order to learn how to play, and  how to represent that data.

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


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

]]> Wed, 22 Jul 2020 11:50:00 -0400 People + AI Research People + AI Research 1280 David’s variant of tic-tac-toe that we’re calling tic-tac-two is only slightly different but turns out to be far more complex. This requires rethinking what the ML system will need in order to learn how to play, and how to represent that data. David’s variant of tic-tac-toe that we’re calling tic-tac-two is only slightly different but turns out to be far more complex. This requires rethinking what the ML system will need in order to learn how to play, and how to represent that data. machine learning, ML, AI, human-centered, reinforcement learning, supervised learning, tic-tac-toe, games, Google, tic tac toe No Head to Head: The Even Bigger ML Smackdown! 8 8 Head to Head: The Even Bigger ML Smackdown! full 5c97fe83-09c8-4b10-899d-fee0f8efb60f https://share.transistor.fm/s/32397484 Yannick and David’s systems play against each other in 500 games. Who’s going to win? And what can we learn about how the ML may be working by thinking about the results?

See the agents play each other in Tic-Tac-Two!


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


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

]]> Yannick and David’s systems play against each other in 500 games. Who’s going to win? And what can we learn about how the ML may be working by thinking about the results?

See the agents play each other in Tic-Tac-Two!


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


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

]]> Wed, 22 Jul 2020 11:55:00 -0400 People + AI Research People + AI Research 1466 Yannick and David’s systems play against each other in 500 games. Who’s going to win? And what can we learn about how the ML may be working by thinking about the results? Yannick and David’s systems play against each other in 500 games. Who’s going to win? And what can we learn about how the ML may be working by thinking about the results? machine learning, ML, AI, human-centered, reinforcement learning, supervised learning, tic-tac-toe, games, Google, tic tac toe No Lessons learned 9 9 Lessons learned full f016b63e-a017-421d-ba19-6eb72a96c81b https://share.transistor.fm/s/2f59a2be What have we learned about machine learning and the human decisions that shape it? And is machine learning perhaps changing our minds about how the world outside of machine learning — also known as the world — works?

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


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

]]> What have we learned about machine learning and the human decisions that shape it? And is machine learning perhaps changing our minds about how the world outside of machine learning — also known as the world — works?

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


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

]]> Wed, 22 Jul 2020 11:58:00 -0400 People + AI Research People + AI Research 1981 What have we learned about machine learning and the human decisions that shape it? And is machine learning perhaps changing our minds about how the world outside of machine learning — also known as the world — works? What have we learned about machine learning and the human decisions that shape it? And is machine learning perhaps changing our minds about how the world outside of machine learning — also known as the world — works? machine learning, ML, AI, human-centered, reinforcement learning, supervised learning, tic-tac-toe, games, Google, tic tac toe No