Branching Time Active Inference: empirical study and complexity class analysis

TL;DR

This paper empirically evaluates branching-time active inference (BTAI), demonstrating its scalability and efficiency in complex tasks compared to standard active inference and other algorithms, while analyzing its complexity class.

Contribution

It provides the first empirical assessment of BTAI, showing its advantages in scalability and performance over traditional active inference and related methods.

Findings

BTAI mitigates local minima with improved preferences and deeper search.

BTAI scales better than standard active inference on larger graphs.

BTAI achieves reward levels comparable to POMCP in the frozen lake environment.

Abstract

Active inference is a state-of-the-art framework for modelling the brain that explains a wide range of mechanisms such as habit formation, dopaminergic discharge and curiosity. However, recent implementations suffer from an exponential complexity class when computing the prior over all the possible policies up to the time horizon. Fountas et al (2020) used Monte Carlo tree search to address this problem, leading to very good results in two different tasks. Additionally, Champion et al (2021a) proposed a tree search approach based on (temporal) structure learning. This was enabled by the development of a variational message passing approach to active inference, which enables compositional construction of Bayesian networks for active inference. However, this message passing tree search approach, which we call branching-time active inference (BTAI), has never been tested empirically. In this paper, we present an experimental study of BTAI in the context of a maze solving agent. In this context, we show that both improved prior preferences and deeper search help mitigate the vulnerability to local minima. Then, we compare BTAI to standard active inference (AcI) on a graph navigation task. We show that for small graphs, both BTAI and AcI successfully solve the task. For larger graphs, AcI exhibits an exponential (space) complexity class, making the approach intractable. However, BTAI explores the space of policies more efficiently, successfully scaling to larger graphs. Then, BTAI was compared to the POMCP algorithm on the frozen lake environment. The experiments suggest that BTAI and the POMCP algorithm accumulate a similar amount of reward. Also, we describe when BTAI receives more rewards than the POMCP agent, and when the opposite is true. Finally, we compared BTAI to the approach of Fountas et al (2020) on the dSprites dataset, and we discussed the pros and cons of each approach.