The explanations of the AI’s algorithms sound pretty simplified, i.e. I wouldn’t be surprised if all these descriptions of how the algorithm works applied to efforts from 10+ years ago. Why did the human-level threshold just get crossed now?
I cannot see anything that is particularly innovative in the paper, though I’m not an expert on this.
Maybe ask people working on poker AI, like Sandholm, directly. Perhaps something like many details of the particular program (and the paper is full of these details) must be assembled in order for this to work cheaply enough to be trained.
This is very interesting, thanks for posting.
The explanations of the AI’s algorithms sound pretty simplified, i.e. I wouldn’t be surprised if all these descriptions of how the algorithm works applied to efforts from 10+ years ago. Why did the human-level threshold just get crossed now?
I cannot see anything that is particularly innovative in the paper, though I’m not an expert on this.
Maybe ask people working on poker AI, like Sandholm, directly. Perhaps something like many details of the particular program (and the paper is full of these details) must be assembled in order for this to work cheaply enough to be trained.