Branching Time Active Inference: Empirical Study And Complexity Class Analysis

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 co

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keychampion2021branching

Related papers

• Deep Active Inference Agents Using Monte-carlo Methods (2020)0.00
• Deconstructing Deep Active Inference (2023)2.26
• Active Inference: Demystified And Compared (2019)15.98
• Active Inference As A Model Of Agency (2024)0.00
• Expanding The Active Inference Landscape: More Intrinsic Motivations In The Perception-action Loop (2018)9.92
• Reward Maximisation Through Discrete Active Inference (2020)10.74
• Sophisticated Inference (2020)14.83
• Active Inference In Hebbian Learning Networks (2023)0.00