Safe and nested subgame solving for imperfect-information games

N Brown, T Sandholm - Advances in neural information …, 2017‏ - proceedings.neurips.cc
In imperfect-information games, the optimal strategy in a subgame may depend on the
strategy in other, unreached subgames. Thus a subgame cannot be solved in isolation and …

[PDF][PDF] Libratus: The Superhuman AI for No-Limit Poker.

N Brown, T Sandholm, S Machine - IJCAI, 2017‏ - onlinecasinoground.nl
Abstract No-limit Texas Hold'em is the most popular variant of poker in the world. Heads-up
no-limit Texas Hold'em is the main benchmark challenge for AI in imperfect-information …

What game are we playing? end-to-end learning in normal and extensive form games

CK Ling, F Fang, JZ Kolter - arxiv preprint arxiv:1805.02777, 2018‏ - arxiv.org
Although recent work in AI has made great progress in solving large, zero-sum, extensive-
form games, the underlying assumption in most past work is that the parameters of the game …

Online convex optimization for sequential decision processes and extensive-form games

G Farina, C Kroer, T Sandholm - … of the AAAI Conference on Artificial …, 2019‏ - ojs.aaai.org
Regret minimization is a powerful tool for solving large-scale extensive-form games. State-of-
the-art methods rely on minimizing regret locally at each decision point. In this work we …

Time and space: Why imperfect information games are hard

N Burch - 2018‏ - era.library.ualberta.ca
Decision-making problems with two agents can be modeled as two player games, and a
Nash equilibrium is the basic solution concept describing good play in adversarial games …

Solving large sequential games with the excessive gap technique

C Kroer, G Farina, T Sandholm - Advances in neural …, 2018‏ - proceedings.neurips.cc
There has been tremendous recent progress on equilibrium-finding algorithms for zero-sum
imperfect-information extensive-form games, but there has been a puzzling gap between …

Mastering strategy card game (legends of code and magic) via end-to-end policy and optimistic smooth fictitious play

W **, Y Zhang, C **ao, X Huang, S Deng… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Deep Reinforcement Learning combined with Fictitious Play shows impressive results on
many benchmark games, most of which are, however, single-stage. In contrast, real-world …

[PDF][PDF] Equilibrium finding for large adversarial imperfect-information games

N Brown - PhD thesis, 2020‏ - reports-archive.adm.cs.cmu.edu
Imperfect-information games model strategic interactions involving multiple agents with
private information. A typical goal in this setting is to approximate an equilibrium in which all …

Reduced space and faster convergence in imperfect-information games via pruning

N Brown, T Sandholm - International conference on machine …, 2017‏ - proceedings.mlr.press
Iterative algorithms such as Counterfactual Regret Minimization (CFR) are the most popular
way to solve large zero-sum imperfect-information games. In this paper we introduce Best …

Large scale learning of agent rationality in two-player zero-sum games

CK Ling, F Fang, JZ Kolter - Proceedings of the AAAI Conference on …, 2019‏ - ojs.aaai.org
With the recent advances in solving large, zero-sum extensive form games, there is a
growing interest in the inverse problem of inferring underlying game parameters given only …