Simulation Data for Decision-Making in Heads-Up Poker Under Uncertainty

This dataset contains simulation data generated for academic research. The study models human decision-making under uncertainty, using heads-up Texas Hold'em as a test domain. The dataset includes results from Monte Carlo simulations of poker games, where the players incorporate strategic parameters such as risk appetite, confidence levels, and bluffing tendencies.

The data is structured to facilitate the analysis of decision-making behaviours in incomplete information games and can be used in the study of game theory, artificial intelligence, behavioural economics, and opponent/entity modelling.

The associated README.md provides additional details on how to interpret the data. Please ensure that the simulation data is first unzipped, and note that the README.md file is best viewed in a dedicated Markdown editor or appropriate application due to known preview issues on Zenodo. There is more information in the codebase used for the generation of this data.

This dataset is useful for research in the following areas:  

Game/Decision Theory: Studying decision-making under uncertainty in incomplete information settings.  

Artificial Intelligence (AI): Training AI models for strategic gameplay and opponent modelling.

Behavioural Economics: Analyzing the impact of risk-taking behaviors on long-term outcomes.

Opponent Modelling: Evaluating how players adjust strategies based on past observations.