I am a legend: Hacking Hearthstone with machine learning Defcon talk wrap-up
I am a legend: Hacking Hearthstone with machine learning Defcon talk wrap-up: video and slides available but no tool. Here is why:
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 our talk, Celine and I show how to use data analysis to find undervalued cards and how to exploit game structure using machine learning to predict your opponent’s deck The video is available below and on YouTube; the slides are on slideshare or available in PDF format.
Why we are not releasing our tool?
One thing you won’t see posted, however, is a 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. They like our research on game/cards balance and are very enthusiastic and supportive about it.
On the other hand, they were very concerned that our real time dashboard that can predict your opponent’s deck will break the game balance by giving that person (that is, whoever has the tool) an unfair advantage. They also expressed concern that such a tool makes the game less fun by taking away some of the decision-making from the player. It was a difficult decision — I 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 your opponent deck, the tool was geared to provide replay functionality to improve your game play and allows to collect data for card balance analysis. The game team told us that adding the replay functionality to Hearthstone is in the roadmap. This convinced us that there is no point to release a subpart version of an upcoming feature.
How do I know more about this research?
If you want to know more about various aspect of the talk you can look at the following blog posts. To know more about analyzing cards balance you can read:
To get more information on how we use machine learning to predict your opponent’s deck you can read this blog post: Predicting Hearthstone opponent deck using machine learning
I invested a lot of energy into this talk, tools and blog posts and feel a little drained so for the next few weeks, I intend to focus on captcha security an SSL before returning to write more about Hearthstone game balance and what are the most important metrics to predict a game outcome. To know when this will be out follow me onTwitter/G+.