A Representation Theorem for Decisions about Causal Models (Dewey)

Added by Deon Garrett over 5 years ago

Given the likely large impact of arti cial general intelligence, a formal theory of intelligence is desirable. To further this research program, we present a representation theorem governing the integration of causal models with decision theory. This theorem puts formal bounds on the applicability of the submodel hypothesis, a normative theory of decision counterfactuals that has previously been argued on a priori and practical grounds, as well as by comparison to theories of counterfactual cognition in humans. We are able to prove four conditions under which the submodel hypothesis holds, forcing any preference between acts to be consistent with some utility function over causal submodels.

paper_58.pdf (270.3 kB)

Replies (1)

RE: A Representation Theorem for Decisions about Causal Models (Dewey) - Added by Ember Moon 14 days ago

AI will largely effect the world. It is conceivable that the course of AGI research will impact the character of this effect essentially, and along these lines that scientists can play a dynamic part in dealing with the effect of AGI. A casual assignment writing service model speaks to occasions and the connections between them as variables and capacities, separately. For every factor, a model contains up to one capacity that figures the estimation of that variable from the estimations of an arrangement of different factors, speaking to the way that occasion relies upon different occasions.