flâneur

Infra-Bayesian physicalism: a formal theory of naturalized induction - LessWrong 2.0 viewer

greaterwrong.com · 23,076 words · saved by 1 readers

This is joint work by Vanessa Kosoy and Alexander "Diffractor" Appel. For the proofs, see 1 and 2. TLDR: We present a new formal decision theory that realizes naturalized induction. Our agents reason in terms of infra-Bayesian hypotheses, the domain of which is the cartesian product of computations and physical states, where the ontology of "physical states" may vary from one hypothesis to another. The key mathematical building block is the "bridge transform", which, given such a hypothesis, extends its domain to "physically manifest facts about computations". Roughly speaking, the bridge transforms determines which computations are executed by the physical universe. In particular, this allows "locating the agent in the universe" by determining on which inputs its own source is executed.

Infra-Bayesian physicalism: a formal theory of naturalized induction - LessWrong 2.0 viewer Infra-Bayesian physicalism: a formal theory of naturalized induction Vanessa Kosoy 30 Nov 2021 22:25 UTC LW: 116 AF: 38 24 comments 42 min read LW link 1 review Infra-Bayesianism AI Agent Foundations Embedded Agency This is joint work by Vanessa Kosoy and Alexander “Diffractor” Appel. For the proofs, see 1 and 2 . TLDR: We present a new formal decision theory that realizes naturalized induction . Our agents reason in terms of infra-Bayesian hypotheses, the domain of which is the cartesian product of com

related reading