B. Hibbard. (2011)cite arxiv:1111.3934Comment: 14 pages.
Abstract
At the recent AGI-11 Conference Orseau and Ring, and Dewey, described
problems, including self-delusion, with the behavior of AIXI agents using
various definitions of utility functions. An agent's utility function is
defined in terms of the agent's history of interactions with its environment.
This paper argues that the behavior problems can be avoided by formulating the
utility function in two steps: 1) inferring a model of the environment from
interactions, and 2) computing utility as a function of the environment model.
The paper also argues that agents will not choose to modify their utility
functions.
%0 Journal Article
%1 hibbard2011
%A Hibbard, Bill
%D 2011
%K modelling programming
%T Model-based Utility Functions
%U http://arxiv.org/ftp/arxiv/papers/1111/1111.3934.pdf
%X At the recent AGI-11 Conference Orseau and Ring, and Dewey, described
problems, including self-delusion, with the behavior of AIXI agents using
various definitions of utility functions. An agent's utility function is
defined in terms of the agent's history of interactions with its environment.
This paper argues that the behavior problems can be avoided by formulating the
utility function in two steps: 1) inferring a model of the environment from
interactions, and 2) computing utility as a function of the environment model.
The paper also argues that agents will not choose to modify their utility
functions.
@article{hibbard2011,
abstract = { At the recent AGI-11 Conference Orseau and Ring, and Dewey, described
problems, including self-delusion, with the behavior of AIXI agents using
various definitions of utility functions. An agent's utility function is
defined in terms of the agent's history of interactions with its environment.
This paper argues that the behavior problems can be avoided by formulating the
utility function in two steps: 1) inferring a model of the environment from
interactions, and 2) computing utility as a function of the environment model.
The paper also argues that agents will not choose to modify their utility
functions.
},
added-at = {2011-11-17T15:03:25.000+0100},
author = {Hibbard, Bill},
biburl = {https://www.bibsonomy.org/bibtex/2862fe04d2a7837b0c64813429ffb9c0d/maxirichter},
description = {Model-based Utility Functions},
interhash = {712efbcb46a41bd7364cb32b2f74694a},
intrahash = {862fe04d2a7837b0c64813429ffb9c0d},
keywords = {modelling programming},
note = {cite arxiv:1111.3934Comment: 14 pages},
timestamp = {2012-01-16T12:26:55.000+0100},
title = {Model-based Utility Functions},
url = {http://arxiv.org/ftp/arxiv/papers/1111/1111.3934.pdf},
year = 2011
}