Publications

Creating accurate computational models of human decision making is a vital step towards the realization of socially intelligent systems capable of both predicting and simulating human behavior. In modeling human decision making, a key factor is the psychological phenomenon known as “framing”, in which the preferences of a decision maker change in response to contextual changes in decision problems. Existing approaches treat framing as a one-dimensional contextual influence based on the perception of outcomes as either gains or losses. However, empirical studies have shown that framing effects are much more multifaceted than one-dimensional views of framing suggest. To address this limitation, we propose an integrative approach to modeling framing which combines the psychological principles of cognitive appraisal theories and decision-theoretic notions of utility and probability. We show that this approach allows for both the identification and computation of the salient contextual factors in a decision as well as modeling how they ultimately affect the decision process. Furthermore, we show that our multi-dimensional, appraisal-based approach can account for framing effects identified in the empirical literature which cannot be addressed by one-dimensional theories, thereby promising more accurate models of human behavior.

Creating agents that act reasonably in uncertain environments is a primary goal of agent-based research. In this work we explore the theory that wishful thinking can be an effective strategy in uncertain and competitive decision scenarios. Specifically, we present the constraints necessary for wishful thinking to outperform Expected Utility Maximization and take instances of popular games from Game-Theoretic literature showing how they relate to our constraints and whether they can benefit from wishful-thinking.

Computational modeling of human belief maintenance and decision-making processes has become increasingly important for a wide range of applications. In this paper, we present a framework for modeling the human capacity for self-deception from a decision-theoretic perspective in which we describe an integrated process of wishful thinking which includes the determination of a desired belief state, the biasing of internal beliefs towards or away from this desired belief state, and the final decision-making process. Finally, we show that in certain situations self-deception can be beneficial.

Computational modeling of human belief maintenance and decision-making processes has become increasingly important for a wide range of applications. We present a framework for modeling the psychological phenomenon of self-deception in a decision-theoretic framework. Specifically, we model the self-deceptive behavior of wishful thinking as a psychological bias towards the belief in a particularly desirable situation or state. By leveraging the structures and axioms of expected utility (EU) we are able to operationalize both the determination and the application of the desired belief state with respect to the decision-making process of expected utility maximization. While we categorize our framework as a descriptive model of human decision making, we show that when specific errors are present, the realized expected utility of an action biased by wishful thinking can exceed that of an action motivated purely by the maximization of expected utility. Finally, in order to provide a descriptive characterization of our framework, we present a discussion of wishful thinking with respect to the Certainty Effect and the Allais Paradox, two specific documented inconsistencies of human behavior. In this discussion we show that our framework has the descriptive flexibility needed to account for both the Certainty Effect and Allais Paradoxes.

Agents face the problem of maintaining and updating their beliefs over the possible mental models (whether goals, plans, activities, intentions, etc.) of other agents in many multiagent domains. Decision-theoretic agents typically model their uncertainty in these beliefs as a probability distribution over their possible mental models of others. They then update their beliefs by computing a posterior probability over mental models conditioned on their observations. We present a novel algorithm for performing this belief update over mental models that are in the form of Partially Observable Markov Decision Problems (POMDPs). POMDPs form a common model for decision-theoretic agents, but there is no existing method for translating a POMDP, which generates deterministic behavior, into a probability distribution over actions that is appropriate for abductive reasoning. In this work, we explore alternate methods to generate a more suitable probability distribution. We use a sample multiagent scenario to demonstrate the different behaviors of the approaches and to draw some conclusions about the conditions under which each is successful.