Sophisticated Inference

Abstract

Active inference offers a first principle account of sentient behaviour, from which special and important cases can be derived, e.g., reinforcement learning, active learning, Bayes optimal inference, Bayes optimal design, etc. Active inference resolves the exploitation-exploration dilemma in relation to prior preferences, by placing information gain on the same footing as reward or value. In brief, active inference replaces value functions with functionals of (Bayesian) beliefs, in the form of an expected (variational) free energy. In this paper, we consider a sophisticated kind of active inference, using a recursive form of expected free energy. Sophistication describes the degree to which an agent has beliefs about beliefs. We consider agents with beliefs about the counterfactual consequences of action for states of affairs and beliefs about those latent states. In other words, we move from simply considering beliefs about 'what would happen if I did that' to 'what would I believe ab

Stats

• citations94
• S2 citations—
• github stars0
• HF likes0
• heat score14.83
• arxiv keyfriston2020sophisticated

Related papers

• Deconstructing Deep Active Inference (2023)2.26
• Active Inference: Demystified And Compared (2019)15.98
• Expanding The Active Inference Landscape: More Intrinsic Motivations In The Perception-action Loop (2018)9.92
• Active Inference As A Model Of Agency (2024)0.00
• Deep Active Inference Agents Using Monte-carlo Methods (2020)0.00
• Contrastive Active Inference (2021)0.00
• Reward Maximisation Through Discrete Active Inference (2020)10.74
• Prior Preference Learning From Experts:designing A Reward With Active Inference (2021)0.00