skip to main content

Title: Mechanistic and Data-Driven Agent-Based Models to Explain Human Behavior in Online Networked Group Anagram Games
In anagram games, players are provided with letters for forming as many words as possible over a specified time duration. Anagram games have been used in controlled experiments to study problems such as collective identity, effects of goal setting, internal-external attributions, test anxiety, and others. The majority of work on anagram games involves individual players. Recently, work has expanded to group anagram games where players cooperate by sharing letters. In this work, we analyze experimental data from online social networked experiments of group anagram games. We develop mechanistic and data driven models of human decision-making to predict detailed game player actions (e.g., what word to form next). With these results, we develop a composite agent-based modeling and simulation platform that incorporates the models from data analysis. We compare model predictions against experimental data, which enables us to provide explanations of human decision-making and behavior. Finally, we provide illustrative case studies using agent-based simulations to demonstrate the efficacy of models to provide insights that are beyond those from experiments alone.
Authors:
; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ;
Award ID(s):
1916670
Publication Date:
NSF-PAR ID:
10204030
Journal Name:
Proceedings of the International Conference on Advances in Social Network Analysis and Mining
Page Range or eLocation-ID:
357-364
ISSN:
2473-991X
Sponsoring Org:
National Science Foundation
More Like this
  1. In a group anagram game, players are provided letters to form as many words as possible. They can also request letters from their neighbors and reply to letter requests. Currently, a single agent-based model is produced from all experimental data, with dependence only on number of neighbors. In this work, we build, exercise, and evaluate enhanced agent behavior models for networked group anagram games under an uncertainty quantification framework. Specifically, we cluster game data for players based on their skill levels (forming words, requesting letters, and replying to requests), perform multinomial logistic regression for transition probabilities, and quantify uncertainty withinmore »each cluster. The result of this process is a model where players are assigned different numbers of neighbors and different skill levels in the game. We conduct simulations of ego agents with neighbors to demonstrate the efficacy of our proposed methods.« less
  2. Anagram games (i.e., word construction games in which players use letters to form words) have been researched for some 60 years. Games with individual players are the subject of over 20 published investigations. Moreover, there are many popular commercial anagram games such as Scrabble. Recently, cooperative team play of anagram games has been studied experimentally. With all of the experimental work and the popularity of such games, it is somewhat surprising that very little modeling of anagram games has been done to predict player behavior/actions in them. We devise a cooperative group anagram game and develop an agent-based modeling andmore »simulation framework to capture player interactions of sharing letters and forming words. Our primary goals are to understand, quantitatively predict, and explain individual and aggregate group behavior, through simulations, to inform the design of a group anagram game experimental platform.« less
  3. Driven by recent successes in two-player, zero-sum game solving and playing, artificial intelligence work on games has increasingly focused on algorithms that produce equilibrium-based strategies. However, this approach has been less effective at producing competent players in general-sum games or those with more than two players than in two-player, zero-sum games. An appealing alternative is to consider adaptive algorithms that ensure strong performance in hindsight relative to what could have been achieved with modified behavior. This approach also leads to a game-theoretic analysis, but in the correlated play that arises from joint learning dynamics rather than factored agent behavior atmore »equilibrium. We develop and advocate for this hindsight rationality framing of learning in general sequential decision-making settings. To this end, we re-examine mediated equilibrium and deviation types in extensive-form games, thereby gaining a more complete understanding and resolving past misconceptions. We present a set of examples illustrating the distinct strengths and weaknesses of each type of equilibrium in the literature, and prove that no tractable concept subsumes all others. This line of inquiry culminates in the definition of the deviation and equilibrium classes that correspond to algorithms in the counterfactual regret minimization (CFR) family, relating them to all others in the literature. Examining CFR in greater detail further leads to a new recursive definition of rationality in correlated play that extends sequential rationality in a way that naturally applies to hindsight evaluation.« less
  4. In a networked anagram game, each team member is given a set of letters and members collectively form as many words as possible. They can share letters through a communication network in assisting their neighbors in forming words. There is variability in behaviors of players, e.g., there can be large differences in numbers of letter requests, of replies to letter requests, and of words formed among players. Therefore, it is of great importance to understand uncertainty and variability in player behaviors. In this work, we propose versatile uncertainty quantification (VUQ) of behaviors for modeling the networked anagram game. Specifically, themore »proposed methods focus on building contrastive models of game player behaviors that quantify player actions in terms of worst, average, and best performance. Moreover, we construct agent-based models and perform agent-based simulations using these VUQ methods to evaluate the model building methodology and understand the impact of uncertainty. We believe that this approach is applicable to other networked games.« less
  5. To make daily decisions, human agents devise their own "strategies" governing their mobility dynamics (e.g., taxi drivers have preferred working regions and times, and urban commuters have preferred routes and transit modes). Recent research such as generative adversarial imitation learning (GAIL) demonstrates successes in learning human decision-making strategies from their behavior data using deep neural networks (DNNs), which can accurately mimic how humans behave in various scenarios, e.g., playing video games, etc. However, such DNN-based models are "black box" models in nature, making it hard to explain what knowledge the models have learned from human, and how the models makemore »such decisions, which was not addressed in the literature of imitation learning. This paper addresses this research gap by proposing xGAIL, the first explainable generative adversarial imitation learning framework. The proposed xGAIL framework consists of two novel components, including Spatial Activation Maximization (SpatialAM) and Spatial Randomized Input Sampling Explanation (SpatialRISE), to extract both global and local knowledge from a well-trained GAIL model that explains how a human agent makes decisions. Especially, we take taxi drivers' passenger-seeking strategy as an example to validate the effectiveness of the proposed xGAIL framework. Our analysis on a large-scale real-world taxi trajectory data shows promising results from two aspects: i) global explainable knowledge of what nearby traffic condition impels a taxi driver to choose a particular direction to find the next passenger, and ii) local explainable knowledge of what key (sometimes hidden) factors a taxi driver considers when making a particular decision.« less