SpinGPT: A Large-Language-Model Approach to Playing Poker Correctly
The Counterfactual Regret Minimization (CFR) algorithm and its variants have enabled the development of pokerbots capable of beating the best human players in heads-up (1v1) cash games and competing with them in six-player formats. However, CFR's computational complexity rises exponentially with the number of players. Furthermore, in games with three or more players, following Nash equilibrium no longer guarantees a non-losing outcome. These limitations, along with others, significantly restrict the applicability of CFR to the most popular formats: tournaments. Motivated by the recent success of Large Language Models (LLM) in chess and Diplomacy, we present SpinGPT, the first LLM tailored to Spin & Go, a popular three-player online poker format. SpinGPT is trained in two stages: (1) Supervised Fine-Tuning on 320k high-stakes expert decisions; (2) Reinforcement Learning on 270k solver-generated hands. Our results show that SpinGPT matches the solver's actions in 78% of decisions (tolerant accuracy). With a simple deep-stack heuristic, it achieves 13.4 +/- 12.9 BB/100 versus Slumbot in heads-up over 30,000 hands (95% CI). These results suggest that LLMs could be a new way to deal with multi-player imperfect-information games like poker.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
PokerBench: Training Large Language Models to become Professional Poker Players
We introduce PokerBench - a benchmark for evaluating the poker-playing abilities of large language models (LLMs). As LLMs excel in traditional NLP tasks, their application to complex, strategic games like poker poses a n…
Are ChatGPT and GPT-4 Good Poker Players? -- A Pre-Flop Analysis
Since the introduction of ChatGPT and GPT-4, these models have been tested across a large number of tasks. Their adeptness across domains is evident, but their aptitude in playing games, and specifically their aptitude i…
Decision MakingDecision Making Under UncertaintyIntegration of Robotics, Computer Vision, and Algorithm Design: A Chinese Poker Self-Playing Robot
This paper presents Chinese Poker Self-Playing Robot, an integrated system enabling a TM5-900 robotic arm to independently play the four-person card game Chinese poker. The robot uses a custom sucker mechanism to pick up…
object-detectionObject DetectionBayes' Bluff: Opponent Modelling in Poker
Poker is a challenging problem for artificial intelligence, with non-deterministic dynamics, partial observability, and the added difficulty of unknown adversaries. Modelling all of the uncertainties in this domain is no…
The Poker-Litigation Game
Is litigation a serious search for truth or simply a game of skill or luck? Although the process of litigation has been modeled as a Prisoner's Dilemma, as a War of Attrition, as a Game of Chicken and even as a simple co…
Game of Poker