Successful Nash equilibrium agent for a three-player imperfect-information game (Q1651920): Difference between revisions
From MaRDI portal
Set profile property. |
Created claim: Wikidata QID (P12): Q129710530, #quickstatements; #temporary_batch_1726327587925 |
||
(3 intermediate revisions by 3 users not shown) | |||
Property / OpenAlex ID | |||
Property / OpenAlex ID: W2797291350 / rank | |||
Normal rank | |||
Property / arXiv ID | |||
Property / arXiv ID: 1804.04789 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Non-cooperative games / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: DeepStack: Expert-level artificial intelligence in heads-up no-limit poker / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: The complexity of two-person zero-sum games in extensive form / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Simple search methods for finding a Nash equilibrium / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: A global Newton method to compute Nash equilibria. / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Equilibrium Points of Bimatrix Games / rank | |||
Normal rank | |||
Property / Wikidata QID | |||
Property / Wikidata QID: Q129710530 / rank | |||
Normal rank |
Latest revision as of 17:29, 14 September 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Successful Nash equilibrium agent for a three-player imperfect-information game |
scientific article |
Statements
Successful Nash equilibrium agent for a three-player imperfect-information game (English)
0 references
10 July 2018
0 references
Summary: Creating strong agents for games with more than two players is a major open problem in AI. Common approaches are based on approximating game-theoretic solution concepts such as Nash equilibrium, which have strong theoretical guarantees in two-player zero-sum games, but no guarantees in non-zero-sum games or in games with more than two players. We describe an agent that is able to defeat a variety of realistic opponents using an exact Nash equilibrium strategy in a three-player imperfect-information game. This shows that, despite a lack of theoretical guarantees, agents based on Nash equilibrium strategies can be successful in multiplayer games after all.
0 references
artificial intelligence
0 references
game theory
0 references
Nash equilibrium
0 references
imperfect information
0 references