A belief game construction plus TB-DAG representation converts imperfect-recall and team zero-sum games into solvable perfect-recall forms, with proven complexity bounds and state-of-the-art benchmark performance.
Superhuman AI for heads-up no-limit poker: Libratus beats top professionals.Science, 359(6374):418–424, 2018
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
GENSTRAT generates fresh imperfect-information card games and a six-axis capability profile plus jaggedness metric to evaluate LLM strategic competence with resistance to saturation.
citing papers explorer
-
Efficient representations for team and imperfect-recall equilibrium computation
A belief game construction plus TB-DAG representation converts imperfect-recall and team zero-sum games into solvable perfect-recall forms, with proven complexity bounds and state-of-the-art benchmark performance.
-
GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models
GENSTRAT generates fresh imperfect-information card games and a six-axis capability profile plus jaggedness metric to evaluate LLM strategic competence with resistance to saturation.