Depth-Limited Solving for Imperfect-Information Games
By Noam Brown, Tuomas Sandholm, Brandon Amos. 2018
93 citations recorded by the source corpus.
A fundamental challenge in imperfect-information games is that states do not have well-defined values. As a result, depth-limited search algorithms used in single-agent settings and perfect-information games do not apply. This paper introduces a principled way to conduct depth-limited solving in imperfect-information games by allowing the opponent to choose among a number of strategies for the remainder of the game at the depth limit. Each one of these strategies results in a different set of values for leaf nodes. This forces an agent to be robust to the different strategies an opponent may employ. We demonstrate the effectiveness of this approach by building a master-level heads-up no-limit Texas hold'em poker AI that defeats two prior top agents using only a 4-core CPU and 16 GB of memory. Developing such a powerful agent would have previously required a supercomputer.
Subfields: Artificial Intelligence, Computer Networks and Communications
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Noam Brown
- Neil Burch
- Tuomas Sandholm
- Adam Lerer
- Michael H. Bowling
- Viliam Lisý
- Martin Schmid
- Vojtěch Kovařík
In Computer Networks and Communications
Citations in the corpus
- Solving Partially Observable Stochastic Games with Public Observations (2019, background): “For finite horizon games, the concept of public states and publicly observed actions creates separated subgames that allow designing limited-lookahead algorithms for imperfect information games (Moravcik et al. 2017; Brown, Sandholm, and Amos 2018).”
- Deep Counterfactual Regret Minimization (2018, methodology): “This solution is referred to as the blueprint strategy [4, 5].”
- Rethinking Formal Models of Partially Observable Multiagent Decision Making (2019, methodology): “As a combination of several recent extensions of the EFG model [8, 20, 6, 37], our formalization removes the need for implementing modern search algorithms in a domain-specific manner.”