More Like this

1. Approaches to Uncertainty Quantification in Building Models of Human Behavior

   Hu, Zhihao ; Deng, Xinwei ; Kuhlman, Chris J ( January 2021 , Winter Simulation Conference)

   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 within 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.
2. On the Modeling and Agent-Based Simulation of a Cooperative Group Anagram Game

   Hu, Zhihao ; Deng, Xinwei ; Goode, Brian J. ; Ramakrishnan, Naren ; Saraf, Parang ; Self, Nathan ; Adiga, Abhijin ; Korkmaz, Gizem ; Kuhlman, Chris J. ; Machi, Dustin ; et al ( January 2019 , Winter Simulation Conference)

   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 and 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.
3. A Bayesian Uncertainty Quantification Approach for Agent-Based Modeling of Networked Anagram Games

   Liu, Xueying ; Hu, Zhihao ; Deng, Xinwei ; Kuhlman, Chris J. ( December 2022 , Proceedings Winter Simulation Conference)

   In group anagram games, players cooperate to form words by sharing letters that they are initially given. The aim is to form as many words as possible as a group, within five minutes. Players take several different actions: requesting letters from their neighbors, replying to letter requests, and forming words. Agent-based models (ABMs) for the game compute likelihoods of each player’s next action, which contain uncertainty, as they are estimated from experimental data. We adopt a Bayesian approach as a natural means of quantifying uncertainty, to enhance the ABM for the group anagram game. Specifically, a Bayesian nonparametric clustering method is used to group player behaviors into different clusters without pre-specifying the number of clusters. Bayesian multi nominal regression is adopted to model the transition probabilities among different actions of the players in the ABM. We describe the methodology and the benefits of it, and perform agent-based simulations of the game.
4. Versatile Uncertainty Quantification of Contrastive Behaviors for Modeling Networked Anagram Games

   https://doi.org/10.1007/978-3-030-93409-5_53  

   Hu, Zhihao ; Deng, Xinwei ; Kuhlman, Chris J ( January 2021 , Complex Networks and their Applications)

   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, the 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.
5. Hindsight and Sequential Rationality of Correlated Play

   Morrill, D ; D'Orazio, R ; Sarfati, R ; Lanctot, M ; Wright, J.R. ; Greenwald, A.R ; Bowling, M. ( May 2021 , Proceedings of the AAAI Conference on Artificial Intelligence)

   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 at 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 inmore »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