scholarly journals Libratus: The Superhuman AI for No-Limit Poker

Author(s):  
Noam Brown ◽  
Tuomas Sandholm

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 games. We present Libratus, the first - and so far only - AI to defeat top human professionals in that game. Libratus's architecture features three main modules, each of which has new algorithms: pre-computing a solution to an abstraction of the game which provides a high-level blueprint for the strategy of the AI, a new nested subgame-solving algorithm which repeatedly calculates a more detailed strategy as play progresses, and a self-improving module which augments the pre-computed blueprint over time.

2020 ◽  
Vol 283 ◽  
pp. 103218 ◽  
Author(s):  
Christian Kroer ◽  
Tuomas Sandholm

Author(s):  
Mitsuo Wakatsuki ◽  
Mari Fujimura ◽  
Tetsuro Nishino

The authors are concerned with a card game called Daihinmin (Extreme Needy), which is a multi-player imperfect information game. Using Marvin Minsky's “Society of Mind” theory, they attempt to model the workings of the minds of game players. The UEC Computer Daihinmin Competitions (UECda) have been held at the University of Electro-Communications since 2006, to bring together competitive client programs that correspond to players of Daihinmin, and contest their strengths. In this paper, the authors extract the behavior of client programs from actual competition records of the computer Daihinmin, and propose a method of building a system that determines the parameters of Daihinmin agencies by machine learning.


Author(s):  
Don Moll ◽  
Edward O. Moll

A wide variety of ingenious methods for collecting river turtles have been developed over time. None requires a particularly high level of technology but many require a great deal of skill, patience, and sometimes physical ability by the collectors, as well as a detailed knowledge of the ecology of the species being sought. Many parallel collecting methods have developed independently in turtle-dependent cultures around the world, leading Nicholls (1977) to state in regard to Bates’s (1863) description of an Amazonian turtle hunt, “With some allowance for small differences in technique, his descriptions provide an accurate image of turtle hunting as it was practiced anytime, anywhere, during the past thousands of years.” We thought that a summary of these techniques with comment upon their variation in different areas and with different species, their effects on populations when this can be ascertained, and examples of their practitioners would be an appropriate addition to our treatment of river turtle exploitation patterns. We will limit our discussion mainly to techniques employed by subsistence and commercial turtlers for obtaining animals and largely omit reference to the growing body of information concerning the collection of turtles for scientific purposes (many of which are largely modifications of the former techniques). For information concerning the latter category the reader is referred to the excellent summary of equipment and techniques by Plummer (1979) and papers by Carr and Marchand (1942), Chaney and Smith (1950), Legler (1960b), Ream and Ream (1966), Wahlquist (1970), Bider and Hoek (1971), Braid (1974), Robinson and Murphy (1975), MacCulloch and Gordon (1978), Iverson (1979), Petokas and Alexander (1979), Vogt (1980b), Frazer et al. (1990), Kennett (1992), Graham and Georges (1996), Jensen (1998), and Kuchling (2003b). Free diving for turtles is of course a time-honored, effective, and nearly cosmopolitan approach to collecting turtles that requires little or no equipment. While diving mask, fins and sophisticated breathing gear certainly enhance the process, they are not required by skilled divers in order to harvest large numbers of turtles.


Author(s):  
Darse Billings ◽  
Aaron Davidson ◽  
Terence Schauenberg ◽  
Neil Burch ◽  
Michael Bowling ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document