Student of Games: A unified learning algorithm for both perfect and imperfect information games · HackerPapers discussions

Student of Games: A unified learning algorithm for both perfect and imperfect information games — mentioned by gwern

Wed, 20 Dec 2023 21:11:15 GMT

The standard AlphaZero doesn't handle that. For that you'd need to graduate to more complex variants like the aforementioned ReBeL, AlphaZe* https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10213697/ or BetaZero https://arxiv.org/abs/2306.00249 or ExIt-OOS https://arxiv.org/abs/1808.10120 or Player of Games https://arxiv.org/abs/2112.03178#deepmind . (You could also move straight to MuZero variations: https://arxiv.org/abs/2106.04615#deepmind https://openreview.net/forum?id=X6D9bAHhBQ1#deepmind https://openreview.net/forum?id=QnzSSoqmAvB )

Paper and discussion history. A mention is not an endorsement.

Student of Games: A unified learning algorithm for both perfect and imperfect information games — mentioned by thomasahle

Mon, 11 Jul 2022 23:32:43 GMT

Bayesian play is not necessarily optimal for imperfect information games. The reason is: You don't only need to play optimally with respect to the information you have observed, you also need to hide your own information and balance those two needs. See the Deep Mind "Player of Games" paper from last year for an agent that takes a more game theoretic approach, which is probably needed for "simpler" games like Poker, that we can play to higher levels of accuracy: https://arxiv.org/pdf/2112.03178.pdf

Paper and discussion history. A mention is not an endorsement.

Student of Games: A unified learning algorithm for both perfect and imperfect information games — mentioned by splonk

Tue, 18 Jan 2022 22:24:50 GMT

Here's a recent paper from DeepMind about their recent efforts towards generalized game solving (caveat: I haven't actually read it yet). https://arxiv.org/pdf/2112.03178.pdf Abstract: "Games have a long history of serving as a benchmark for progress in artificial intelligence. Recently, approaches using search and learning have shown strong performance across a set of perfect information games, and approaches using game-theoretic reasoning and learning have shown strong performance for specific imperfect information poker variants. We introduce Player of Games, a general-purpose algorithm…

Paper and discussion history. A mention is not an endorsement.

Student of Games: A unified learning algorithm for both perfect and imperfect information games — HN submission

Wed, 08 Dec 2021 05:52:14 GMT

Player of Games

364 points; 231 discussion replies on HN. Paper and source history. A submission is not an endorsement.