Addressing the Subsumption Thesis: A Formal Bridge between Microeconomics and Active Inference
As a unified theory of sentient behaviour, active inference is formally intertwined with multiple normative theories of optimal behaviour. Specifically, we address what we call the subsumption thesis: The claim that expected utility from economics, as an account of agency, is subsumed by active inference. To investigate this claim, we present multiple examples that challenge the subsumption thesis. To formally compare these two accounts of agency, we analyze the objective functions for MDPs and POMDPs. By imposing information-theoretic rationality bounds (ITBR) on the expected utility agent, we find that the resultant agency is equivalent to that of active inference in MDPs, but slightly different in POMDPs. Rather than being strictly resolved, the subsumption thesis motivates the construction of a formal bridge between active inference and expected utility. This highlights the necessary formal assumptions and frameworks to make these disparate accounts of agency commensurable.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Imparo is complete by inverse subsumption
In Inverse subsumption for complete explanatory induction Yamamoto et al. investigate which inductive logic programming systems can learn a correct hypothesis $H$ by using the inverse subsumption instead of inverse entai…
Inductive logic programmingNeurOWL: An LLM-Based Neural-symbolic Framework for Incomplete OWL Ontology Reasoning
OWL ontologies provide a formal knowledge representation framework that enables semantic reasoning, and have been widely adopted across domains such as healthcare and bioinformatics. In practice, however, real-world onto…
Fuzzy order-sorted feature logic
Order-Sorted Feature (OSF) logic is a knowledge representation and reasoning language based on function-denoting feature symbols and set-denoting sort symbols ordered in a subsumption lattice. OSF logic allows the constr…
RelationBRIDGE: Building Representations In Domain Guided Program Synthesis
Large language models can generate plausible code, but remain brittle for formal verification in proof assistants such as Lean. A central scalability challenge is that verified synthesis requires consistent artifacts acr…
Program SynthesisLarge-scale Taxonomy Induction Using Entity and Word Embeddings
Taxonomies are an important ingredient of knowledge organization, and serve as a backbone for more sophisticated knowledge representations in intelligent systems, such as formal ontologies. However, building taxonomies m…
Word Embeddings