Benjamin Nye

Sociocultural Games for Training and Analysis

This paper presents a theory for role-playing simulation games intended to support analysts (and trainees) with generating and testing alternative competing hypotheses on how to influence world conflict situations. Simulated leaders and followers capable of playing these games are implemented in a cognitive modeling framework, called the Performance Moderator Function Server (PMFserv), which covers value systems, personality and cultural factors, emotions, relationships, perception, stress/coping style, and decision making. Of direct interest, as Section I-A explains, is codification and synthesis of best-of-breed social-science models within PMFserv to improve the internal validity of agent implementations. Sections II and III present this for leader profiling instruments and group-membership decision making, respectively. Section IV then offers two real-world case studies (The Third Crusade and SE Asia Today) where agent models are subjected to Turing and correspondence tests under each case study. In sum, substantial effort on game realism, best-of-breed social-science models, and agent validation efforts is essential if analysis and training tools are to help explore cultural issues and alternative ways to influence outcomes. Such exercises, in turn, are likely to improve the state of the science as well.

Rich socio-cognitive agents for immersive training environments: case of NonKin Village

Demand is on the rise for scientifically based human-behavior models that can be quickly customized and inserted into immersive training environments to recreate a given society or culture. At the same time, there are no readily available science model-driven environments for this purpose (see survey in Sect. 2). In researching how to overcome this obstacle, we have created rich (complex) socio-cognitive agents that include a large number of social science models (cognitive, sociologic, economic, political, etc) needed to enhance the realism of immersive, artificial agent societies. We describe current efforts to apply model-driven development concepts and how to permit other models to be plugged in should a developer prefer them instead. The current, default library of behavioral models is a metamodel, or authoring language, capable of generating immersive social worlds. Section 3 explores the specific metamodels currently in this library (cognitive, socio-political, economic, conversational, etc.) and Sect. 4 illustrates them with an implementation that results in a virtual Afghan village as a platform-independent model. This is instantiated into a server that then works across a bridge to control the agents in an immersive, platform-specific 3D gameworld (client). Section 4 also provides examples of interacting in the resulting gameworld and some of the training a player receives. We end with lessons learned and next steps for improving both the process and the gameworld. The seeming paradox of this research is that as agent complexity increases, the easier it becomes for the agents to explain their world, their dilemmas, and their social networks to a player or trainee.

Gaming and Simulating Ethno-Political Conflicts

This chapter begins by describing a universally recurring socio-cultural “game” of inter-group competition for control of resources. It next describes efforts to author software agents able to play the game as real humans would - which suggests the ability to study alternative ways to influence them, observe PMESII effects, and potentially understand how best to alter the outcomes of potential conflict situations. These agents are unscripted, but use their decision making to react to events as they unfold and to plan out responses. For each agent, a software called PMFserv operates its perception and runs its physiology and personality/value system to determine fatigue and hunger, injuries and related stressors, grievances, tension buildup, impact of rumors and speech acts, emotions, and various collective and individual action decisions. The chapter wraps up with a correspondence test from a SE Asian ethnic conflict, the results of which indicate significant correlation between real and agentbased outcomes.

Cognitive modeling of socially transmitted affordances: a computational model of behavioral adoption tested against archival data from the Stanford Prison Experiment

Social learning and adoption of new affordances govern the rise of new a variety of behaviors, from actions as mundane as dance steps to those as dangerous as new ways to make improvised explosive device (IED) detonators. Traditional diffusion models and social network structures fail to adequately explain who would be likely to imitate new behavior and why some agents adopt the behavior while others do not. To address this gap, a cognitive model was designed that represents well-known socio-cognitive factors of attention, social influence, and motivation that influence learning and adoption of new behavior. This model was implemented in the Performance Moderator Function Server (PMFServ) agent-based cognitive architecture, enabling the creation of simulations where affordances spread memetically through cognitive mechanisms. This approach models facets of behavioral adoption that have not been explored by existing architectures: unintentional learning, multi-layered social and environmental attention cues, and contextual adoption. To examine the effectiveness of this model, its performance was tested against data from the Stanford Prison Experiment collected from the Archives of the History of American Psychology.

Social learning and adoption of new behavior in a virtual agent society

Social learning and adoption of new behavior govern the rise of a variety of behaviors: from actions as mundane as dance steps to those as dangerous as new ways to make IED detonators. However, agents in immersive virtual environments lack the ability to realistically simulate the spread of new behavior. To address this gap, a cognitive model was designed that represents the well-known socio-cognitive factors of attention, social influence, and motivation that influence learning and the adoption of a new behavior. To explore the effectiveness of this model, simulations modeled the spread of two competing memes in Hamariyah, an archetypal Iraqi village developed for cross-cultural training. Diffusion and clustering analyses were used to examine adoption patterns in these simulations. Agents produced well-defined clusters of early versus late adoption based on their social influences, personality, and contextual factors, such as employment status. These findings indicate that the spread of behavior can be simulated plausibly in a virtual agent society and has the potential to increase the realism of immersive virtual environments.

Simulation-Based training of ill-defined social domains: the complex environment assessment and tutoring system (CEATS)

Socio-cultural problems have special challenges that complicate training design. Problems in these domains have been called “wicked problems” due to their intractability [4]. Such problems are ill-defined: characterized by conflicting stakeholder values, disagreements over solutions, and interconnectedness between problems. Simulation-based learning can be used to explore these problems, but assessment is a bottleneck for training ill-defined domains. Problems in ill-defined domains are heterogeneous: some problems have clear right and wrong answers, but others are subjective, context-dependent, or emergent. A possible solution is hybrid tutoring, which combines multiple tutoring approaches [2]. A hybrid tutor could match different pedagogical interventions for different types of problems. However, hybrid tutoring lacks established design principles for matching domain problems with suitable interventions. The Complex Environment Assessment and Tutoring System (CEATS) follows two principles to support hybrid tutoring. First, semantic interfaces are used to decouple components, transforming the simulation environment into meaningful metrics. Assessments use metrics as evidence to calculate measures about domain concept qualities. The second principle is to support families of assessments. Together, this design decouples assessments from the simulation and embeds meta-data to make them meaningful for reporting and tutoring modules. The Complex Environment Assessment and Tutoring System uses metrics as a semantic API for the learning environment. This allows different environments (e.g. simulation vs database) to share the same metric specifications, but implement their own function and query implementations. A metrics engine currently exists for use with a real-time simulation (described below) and a second metrics engine is being added to support metrics on a database of simulation runs.