Let's build a video game, train a bot to play it, and deploy it on a smartphone in 30 minutes
By Paris Buttfield-Addison

In this session, we'll build a little smartphone game, train a bot to play it using reinforcement learning with Python and TensorFlow, and deploy it to a smartphone. In 30 minutes we'll show you how easy it is to add machine learning (ML)-powered intelligence to video games and simulations, and how useful it can be to visualize ML problems. It'll be fun, and you'll learn the fundamentals of ML.

Saturday 4 p.m.–4:30 p.m.

In this session, we’ll build a little smartphone game, train a bot to play it using reinforcement learning, Python, and TensorFlow, and deploy it to a smartphone.

In 30minutes. We’ll show you how easy it is to add ML-powered intelligence to video games or simulations, and how inference on smartphones is easier than it’s ever been: modern, powerful tools like Unity’s ML-Agents, Python, and TensorFlow make the complex easy. And it’s a lot of fun.

First, we’ll spend 10 minutes of the session:

  • showcasing the absolute basics game engines
  • creating an arcade game, live on stage
  • adding some art, to make the game look pretty!

Second, we’ll spend 10 minutes of the session:

  • implementing an agent, using Python and TensorFlow, that is rewarded for playing the game
  • training the agent to play
  • giving the agent some character

Finally, we’ll spend the last 10 minutes of the session:

  • preparing our trained model for deployment onto a smartphone
  • building the game and optimizing both the gameplay and ML-components for a smartphone
  • showing the audience the game, running live on a phone!

This is an engaging, fast-paced, and surprisingly in-depth exploration of how powerful modern game engines can be used for quick, relatively easy, but incredibly powerful state of the art machine learning and training, and how powerful inference on-device is, for mobile AI.

You don’t need to be a game developer to see the benefits. Join us for 30minutes of rapid live coding, and engaging banter while we show what’s really possible with Python, TensorFlow for ML, game engines/simulations, and mobile devices!

Paris Buttfield-Addison

Dr Paris Buttfield-Addison is co-founder of Secret Lab, a game development studio based in beautiful Hobart, Australia. Secret Lab builds games and game development tools, including the multi-award-winning ABC Play School iPad games, the BAFTA- and IGF-winning Night in the Woods, the Qantas airlines Joey Playbox games, and the tremendously popular open source narrative game framework, Yarn Spinner. Previously, Paris was mobile product manager for Meebo (acquired by Google). Paris particularly enjoys game design, statistics, law, machine learning, and human-centered technology research and writes technical books on mobile and game development (more than 20 so far) for O’Reilly Media. He holds a degree in medieval history and a PhD in computing.