Conference on Cognitive Computational Neuroscience

Active inference is a model for inferring actions based on the free energy principle (FEP), which has been proposed as a unified framework for understanding perception, action, and learning in the brain. Active inference has previously been used to model ecologically important tasks such as navigation and planning, but scaling active inference to solving complex large-scale problems in real-world environments has remained a challenge. Inspired by the existence of multi-scale hierarchical representations in the brain, we propose a model for planning of actions based on hierarchical active inference. The model combines a hierarchical internal model of the environment with successor representations for efficient planning. We present results demonstrating (1) how lower-level successor representations can be used to learn higher-level abstract states, (2) how planning based on active inference at the lower-level can be used to bootstrap and learn higher-level abstract actions, and (3) how these learned higher-level abstract states and actions can facilitate efficient planning. Our results represent to our knowledge the first application of hierarchical state and action abstractions to active inference in FEP-based theories of brain function.