PROJECT TITLE :
Modeling Human Recursive Reasoning Using Empirically Informed Interactive Partially Observable Markov Decision Processes
Recursive reasoning of the shape what do I think that you're thinking that that I assume (and therefore on) arises often whereas acting in multiagent settings. Previously, multiple experiments studied the extent of recursive reasoning usually displayed by humans while playing sequential general-add and fixed-total, 2-player games. The results show that subjects experiencing a general-sum strategic game show 1st or second level of recursive thinking with the first level being a lot of distinguished. But, if the sport is made less complicated and additional competitive with mounted-sum payoffs, subjects predominantly attributed initial-level recursive thinking to opponents thereby acting using second level. In this text, we model the behavioral knowledge obtained from the studies using the interactive partially observable Markov call process, appropriately simplified and augmented with well-known models simulating human learning and decision. We tend to experiment with knowledge collected at totally different points in the study to be told the models parameters. Accuracy of the predictions by our models is evaluated by comparing them with the observed study information, and the significance of the match is demonstrated by comparing the mean squared error of our model predictions with those of a random hypothesis. Accuracy of the predictions by the models counsel that these could be viable ways for computationally modeling strategic behavioral data in an exceedingly general means. While we have a tendency to do not claim the cognitive plausibility of the models within the absence of a lot of evidence, they represent promising steps toward understanding and computationally simulating strategic human behavior.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here