@Article{Pankov2007,
author = {Pankov, Sergey}, 
title = {A computational approximation to the AIXI model}, 
journal = {}, 
volume = {}, 
number = {}, 
pages = {12}, 
year = {2007}, 
abstract = {Universal induction solves in principle the problem of choosing a to achieve optimal inductive inference. The AIXI theory, which control theory and universal induction, solves in principle the problem of optimal behavior of an intelligent agent. A practically most and very challenging problem is to nd a computationally ecient (if optimal) approximation for the optimal but incomputable AIXI theory. We propose such an approximation based on a Monte Carlo algorithm that samples programs according to their algorithmic probability. The approach is specically designed to deal with real world problems (agent processes observed data and makes plans over range of time scales) under limited computational resources.}, 
location = {}, 
keywords = {}}

{"_id":"mpgeAaxeHxc9xfJop","bibbaseid":"pankov-acomputationalapproximationtotheaiximodel-2007","authorIDs":[],"author_short":["Pankov, S."],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Pankov"],"firstnames":["Sergey"],"suffixes":[]}],"title":"A computational approximation to the AIXI model","journal":"","volume":"","number":"","pages":"12","year":"2007","abstract":"Universal induction solves in principle the problem of choosing a to achieve optimal inductive inference. The AIXI theory, which control theory and universal induction, solves in principle the problem of optimal behavior of an intelligent agent. A practically most and very challenging problem is to nd a computationally ecient (if optimal) approximation for the optimal but incomputable AIXI theory. We propose such an approximation based on a Monte Carlo algorithm that samples programs according to their algorithmic probability. The approach is specically designed to deal with real world problems (agent processes observed data and makes plans over range of time scales) under limited computational resources.","location":"","keywords":"","bibtex":"@Article{Pankov2007,\nauthor = {Pankov, Sergey}, \ntitle = {A computational approximation to the AIXI model}, \njournal = {}, \nvolume = {}, \nnumber = {}, \npages = {12}, \nyear = {2007}, \nabstract = {Universal induction solves in principle the problem of choosing a to achieve optimal inductive inference. The AIXI theory, which control theory and universal induction, solves in principle the problem of optimal behavior of an intelligent agent. A practically most and very challenging problem is to nd a computationally ecient (if optimal) approximation for the optimal but incomputable AIXI theory. We propose such an approximation based on a Monte Carlo algorithm that samples programs according to their algorithmic probability. The approach is specically designed to deal with real world problems (agent processes observed data and makes plans over range of time scales) under limited computational resources.}, \nlocation = {}, \nkeywords = {}}\n\n\n","author_short":["Pankov, S."],"key":"Pankov2007","id":"Pankov2007","bibbaseid":"pankov-acomputationalapproximationtotheaiximodel-2007","role":"author","urls":{},"downloads":0},"bibtype":"article","biburl":"https://gist.githubusercontent.com/stuhlmueller/a37ef2ef4f378ebcb73d249fe0f8377a/raw/6f96f6f779501bd9482896af3e4db4de88c35079/references.bib","creationDate":"2020-01-27T02:13:34.604Z","downloads":0,"keywords":[],"search_terms":["computational","approximation","aixi","model","pankov"],"title":"A computational approximation to the AIXI model","year":2007,"dataSources":["hEoKh4ygEAWbAZ5iy"]}