Inferring Hierarchical Structure in Multi-Room Maze Environments

TL;DR

This paper presents a hierarchical active inference model that enables efficient exploration and navigation in multi-room maze environments by inferring environmental structure from pixel observations.

Contribution

It introduces a novel three-layer hierarchical model combining cognitive maps with curiosity-driven exploration and goal-oriented behavior.

Findings

Effective exploration in mini-grid environments

Successful inference of environment structure from pixel data

Enhanced navigation performance through hierarchical reasoning

Abstract

Cognitive maps play a crucial role in facilitating flexible behaviour by representing spatial and conceptual relationships within an environment. The ability to learn and infer the underlying structure of the environment is crucial for effective exploration and navigation. This paper introduces a hierarchical active inference model addressing the challenge of inferring structure in the world from pixel-based observations. We propose a three-layer hierarchical model consisting of a cognitive map, an allocentric, and an egocentric world model, combining curiosity-driven exploration with goal-oriented behaviour at the different levels of reasoning from context to place to motion. This allows for efficient exploration and goal-directed search in room-structured mini-grid environments.