Structured Active Inference (Extended Abstract)

TL;DR

This paper introduces structured active inference, a formal framework using categorical systems theory to enable complex, verifiable, and hierarchical agent interactions and goal management within generative models.

Contribution

It formalizes active inference with structured interfaces and categorical logic, expanding capabilities for agent interaction, management, and verification.

Findings

Enables agents with structured, compositional interfaces.

Allows formal verification of policies.

Supports hierarchical and meta-agent architectures.

Abstract

We introduce structured active inference, a large generalization and formalization of active inference using the tools of categorical systems theory. We cast generative models formally as systems "on an interface", with the latter being a compositional abstraction of the usual notion of Markov blanket; agents are then 'controllers' for their generative models, formally dual to them. This opens the active inference landscape to new horizons, such as: agents with structured interfaces (e.g. with 'mode-dependence', or that interact with computer APIs); agents that can manage other agents; and 'meta-agents', that use active inference to change their (internal or external) structure. With structured interfaces, we also gain structured ('typed') policies, which are amenable to formal verification, an important step towards safe artificial agents. Moreover, we can make use of categorical logic to describe express agents' goals as formal predicates, whose satisfaction may be dependent on the interaction context. This points towards powerful compositional tools to constrain and control self-organizing ensembles of agents.