Download this episode
Do you want to recommend a news story? Have your interface optimize for its user? Maybe you just wish that when you used machine learning it actually worked in deployment? In all of these cases, you want to make decisions amongst a set of actions based on a context to optimize an outcome. Doing this consistently and effectively requires a system that combines exploration and learning together to adaptively discover performant policies. We have created that system and deployed it several ways with great results. That system can now be used by you, most easily for simple content personalization, but more generally in any system where you have many repeated events where context matters in making a decision and the quality of that decision can be evaluated.
Available formats for this video:
Actual format may change based on video formats available and browser capability.