Creating engaging, interactive, and immersive synthetic characters is a difficult task and evaluating the success of a synthetic character is often even more difficult. The later problem is solved by extending Turing's Imitation Game thusly: computational construct should be evaluated based on the criteria of how well the character can mimic a human. In order to accomplish a successful evaluation of the proposed metric, synthetic characters must be consistently believable and capable of role-appropriate emotional expression. The author believes traditional synthetic characters must be improved to meet this goal. For a synthetic character to be believable, human users must be able to perceive a link between the mental state of the character and its behaviors. That is to say, synthetic characters must possess intentionality. In addition to intentionality, the mental state of the character must be human-like in order to provide an adequate frame of reference for the human users' internal simulations, to wit, the character's mental state must be comprised of a synthetic model of personality, of personality dynamics, and of cognition, each of which must be psychologically valid and of sufficient fidelity for the type of character represented. The author proposes that synthetic characters possessing these three models are more accurately described as synthetic personalities. The author proposes and implements computational models of personality, personality dynamics, and cognition in order to evaluate the psychological veracity of these models and computational equivalence between the models and the implementation as a first step in the process of creating believable synthetic personalities.

Behavioral animation has become popular for creating virtual characters that are autonomous agents and thus self-animating. This is useful for lessening the workload of human animators, populating virtual environments with interactive agents, etc. Unfortunately, current behavioral animation techniques suffer from three key problems: (1) deliberative behavioral models (i.e., cognitive models) are slow to execute; (2) interactive virtual characters cannot adapt online due to interaction with a human user; (3) programming of behavioral models is a difficult and time-intensive process. This dissertation presents a collection of papers that seek to overcome each of these problems. Specifically, these issues are alleviated through novel machine learning schemes. Problem 1 is addressed by using fast regression techniques to quickly approximate a cognitive model. Problem 2 is addressed by a novel multi-level technique composed of custom machine learning methods to gather salient knowledge with which to guide decision making. Finally, Problem 3 is addressed through programming-by-demonstration, allowing a non technical user to quickly and intuitively specify agent behavior.

Cognitive and behavioral models have become popular methods to create autonomous self-animating characters. Creating these models presents the following challenges: (1) Creating a cognitive or behavioral model is a time intensive and complex process that must be done by an expert programmer (2) The models are created to solve a specific problem in a given environment and because of their specific nature cannot be easily reused. Combining existing models together would allow an animator, without the need of a programmer, to create new characters in less time and would be able to leverage each model's strengths to increase the character's performance, and to create new behaviors and animations. This thesis provides a framework that can aggregate together existing behavioral and cognitive models into an ensemble. An animator only has to rate how appropriately a character performed and through machine learning the system is able to determine how the character should act given the current situation. Empirical results from multiple case studies validate the approach taken.