> The main difference in Hanabi is that there is no “cheap-talk” communication channel: any signalling must be done through the actions played. It is therefore more similar in spirit to learning how to relay information to partners in the bidding round of bridge.
Jakob, why did you choose Hanabi instead of bridge itself? Bridge is obviously much more widely known and seems to present similar challenges.
To add on to the reasons mentioned by others (Hanabi is simpler, purely cooperative, etc), I'll point out that Hanabi is fairly popular with young CS types, especially the ones interested in ML and AI, much more so than Bridge which is understandably seen as old fashioned. My source for this statement being that I'm friends with a lot of such people and was roommates with someone who now works for Deep Mind, and have learned first hand and shared in the generalized Hanabi obsession. Perhaps it's just my localized experience and I'm exaggerating the popularity of the game. But I think it's telling that I wasn't the least big surprised when I saw this game mentioned as the next candidate Deep Mind would tackle.
Does it much matter that the topic being studied is one you have experience with and a passion for? Perhaps more than we might think.
Hanabi is fully cooperative and entirely focused on communication. I think it's good to have a testbed that isolates these challenges, rather confounding them with the zero-sum (competitive) aspect of Bridge. Having said this, I do believe Bridge is a good testbed to put the different methods together.
> The main difference in Hanabi is that there is no “cheap-talk” communication channel: any signalling must be done through the actions played. It is therefore more similar in spirit to learning how to relay information to partners in the bidding round of bridge.
Jakob, why did you choose Hanabi instead of bridge itself? Bridge is obviously much more widely known and seems to present similar challenges.