Branching Time Active Inference: empirical study and complexity class analysis

by   Théophile Champion, et al.

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 (space and time) 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 structure learning. This was enabled by the development of a variational message passing approach to active inference (Champion et al., 2021b), 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 the approach (Champion et al., 2021a) 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 (AI) on a graph navigation task. We show that for small graphs, both BTAI and AI successfully solve the task. For larger graphs, AI exhibits an exponential (space) complexity class, making the approach intractable. However, BTAI explores the space of policies more efficiently, successfully scaling to larger graphs.


Branching Time Active Inference: the theory and its generality

Over the last 10 to 15 years, active inference has helped to explain var...

Multi-Modal and Multi-Factor Branching Time Active Inference

Active inference is a state-of-the-art framework for modelling the brain...

Branching Time Active Inference with Bayesian Filtering

Branching Time Active Inference (Champion et al., 2021b,a) is a framewor...

Realising Active Inference in Variational Message Passing: the Outcome-blind Certainty Seeker

Active inference is a state-of-the-art framework in neuroscience that of...

Chance-Constrained Active Inference

Active Inference (ActInf) is an emerging theory that explains perception...

A comparative study of the performance of different search algorithms on FOON graphs

A robot finds it really hard to learn creatively and adapt to new unseen...

Improved Algorithm for the Network Alignment Problem with Application to Binary Diffing

In this paper, we present a novel algorithm to address the Network Align...

Please sign up or login with your details

Forgot password? Click here to reset