Cultural advice

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

Aboriginal and Torres Strait Islander peoples are advised that ANU Library collections may include images, names, voices, and other representations of deceased persons.

Material in the collection may contain terms, language or views that reflect the period in which the item was created and may be considered inappropriate today.

Asymptotically Optimal Agents

Date

Authors

Lattimore, Tor

Hutter, Marcus

Publisher

Springer

Abstract

Artificial general intelligence aims to create agents capable of learning to solve arbitrary interesting problems. We define two versions of asymptotic optimality and prove that no agent can satisfy the strong version while in some cases, depending on discounting, there does exist a non-computable weak asymptotically optimal agent.

Keywords

Keywords: Asymptotic optimality; general discounting; General Intelligence; Rational agents; sequential decision theory; Algorithms; Decision theory; Reinforcement learning; Optimization artificial general intelligence; asymptotic optimality; general discounting; Rational agents; reinforcement learning; sequential decision theory

URI

http://hdl.handle.net/1885/38019

Collections

ANU Research Publications

Source

Lecture Notes in Artificial Intelligence 6925

Type

Conference paper

Access Statement

Open Access

DOI

10.1007/978-3-642-24412-4_29

Downloads

File

Description

01_Lattimore_Asymptotically_Optimal_A_2011.pdf (259.84 KB)