I am a legend: Hacking Hearthstone with machine-learning Defcon talk wrap-up: video and slides available but no tool.

Good news! The video and slides of our talk on how to use machine learning for Hearthstone are finally available for those who couldn't come to Defcon.

In this talk, Celine and I demonstrate how to use data analysis to find undervalued cards and how to exploit the game’s structure using machine learning to predict the opponent's deck. You can see the slides on Slideshare and the video on YouTube:

Why are you not releasing your tool?

One thing you won't see posted, however, is the software tool that we promised to release during our Defcon presentation. Following Defcon, we had a series of conversations with the Hearthstone team about our research. Apparently the email that I sent prior to Defcon didn't reach the right person.

Here is a short summary of what they told us:

  1. They like our research on the game/cards balance and are very enthusiastic and supportive about it.

  2. On the other hand, they were very concerned that our real-time dashboard, which can predict an opponent's deck, will break the game balance by giving whoever has the tool an unfair advantage.

  3. They also expressed concern that such a tool makes the game less fun by taking away some decision-making from the player.

It was a difficult decision - I have invested a lot of our time building our real-time dashboard tool with Celine - but we agree with the Hearthstone team and will not release the tool publicly.

How about game replays?

Beside predicting an opponent’s deck, the tool was geared to provide replay functionality to improve your game play and it allows us to collect data for our card balance analysis.

However, the game team told us that adding replay functionality to Hearthstone was in the road map. Additionally as of October 2016, HSReplay offers a better way to collect replays, which is why we won't release a tool to do this either.

How can I learn more about this research?

A more “scientific” treatment of some of the talk results are published in this research paper.

If you want to learn more about applying machine learning to Hearthstone, you can read the following blog posts:

  1. How to price Hearthstone cards: Presents the card pricing model used in the follow-up posts to find undervalued cards.
  2. How to find undervalued cards automatically: Builds on the pricing model to find undervalued cards automatically.
  3. Pricing special cards: Showcases how to appraise the cost of cards that have complex effects, like VanCleef.
  4. Predicting your Hearthstone’s opponent deck: Demonstrates how to use machine learning to predict what the opponent will play.
  5. Predicting Hearthstone game outcomes with machine learning: Discusses how to apply machine learning to predict game outcomes.