A Variational Approach to Scripts

Abstract

This paper proposes a formal reconstruction of the script construct by leveraging the active inference framework, a behavioral modeling framework that casts action, perception, emotions, and attention as processes of (Bayesian or variational) inference. We propose a first principles account of the script construct that integrates its different uses in the behavioral and social sciences. We begin by reviewing the recent literature that uses the script construct. We then examine the main mathematical and computational features of active inference. Finally, we leverage the resources of active inference to offer a formal model of scripts. Our integrative model accounts for the dual nature of scripts (as internal, psychological schema used by agents to make sense of event types and as constitutive behavioral categories that make up the social order) and also for the stronger and weaker conceptions of the construct (which do and do not relate to explicit action sequences, respectively).

Keywords: Bayesian reasoning; active inference; script theory; social scripts; variational free-energy principle.

FIGURE 1

A simple generative model for policy selection. This schematic depicts a generative model for policy selection. It represents probabilistic beliefs about how observations are related to the states that cause them (the likelihood matrix, which is denoted A), beliefs about the manner in which states of the world evolve over time (the state transition matrix, denoted B), and beliefs about states prior to sampling the world (prior beliefs, denoted D). Preferences over outcomes (C) are not depicted. From Friston et al. (2017b). For ease of visualization, we do not present the hierarchical structure of the generative process. The reader should assume that there structure of the generative process will include multiple levels. The important aspect of this schematic is to present the manner in which the generative model and the generative process interact with one another. The only reason we present multiple levels of the generative model is that two levels allows for a description of all the inner components of the script. Only one level of the generative process is needed to describe the external component (even though we should assume multiple levels of the generative process). The higher levels of a model constrain possible inference at the lower levels by unfolding over slower timescales and by setting the prior beliefs about initial states D at the lower level–that contextualize the ensuing state transitions or narratives. In such models, posterior estimates of successive states at the lower level become data or observations for inference at the level above.

FIGURE 2

Heuristic description of the generative model of the niche and of the agent. This schematic should be read as a heuristic “formal flowchart” of the biasing relation between priors and likelihood in generative model, rather than as a standard (probabilistic graphical) generative model. Weak scripts correspond to the knowledge about event types and their relation to sensory data available to the agent. Computationally, these correspond to priors and likelihoods (denoted as squares 1, 3, 4, 8, 7, 11, 9) that are combined to infer sequences of hidden states and the action policy (denoted as open circles 2, 5, 6, 10). Note that, for instance, “D1” in the bottom portion of the schematic is not the same as “D1” in the top section since the former is an attribute of the generative process, and the latter is an attribute of the generative model. We use the notion “D1” in both cases to help the unfamiliar reader to visualize the mirroring relation between the generative process and model.