<abstract xmlns="http://www.w3.org/1999/xhtml"><p>We propose a new measure of intelligence for general reinforcement learning agents, based on the notion that an agent’s environment can change at any step of execution of the agent. That is, an agent is considered to be interacting with its environment in real-time. In this sense, the resulting intelligence measure is more general than the universal intelligence measure (Legg and Hutter, 2007) and the anytime universal intelligence test (Hernández-Orallo and Dowe, 2010). A major advantage of the measure is that an agent’s computational complexity is factored into the measure in a natural manner. We show that there exist agents with intelligence arbitrarily close to the theoretical maximum, and that the intelligence of agents depends on their parallel processing capability. We thus believe that the measure can provide a better evaluation of agents and guidance for building practical agents with high intelligence.</p></abstract>

We propose a new measure of intelligence for general reinforcement learning agents, based on the notion that an agent’s environment can change at any step of execution of the agent. That is, an agent is considered to be interacting with its environment in real-time. In this sense, the resulting intelligence measure is more general than the universal intelligence measure (Legg and Hutter, 2007) and the anytime universal intelligence test (Hernández-Orallo and Dowe, 2010). A major advantage of the measure is that an agent’s computational complexity is factored into the measure in a natural manner. We show that there exist agents with intelligence arbitrarily close to the theoretical maximum, and that the intelligence of agents depends on their parallel processing capability. We thus believe that the measure can provide a better evaluation of agents and guidance for building practical agents with high intelligence.

A Measure of Real-Time Intelligence

School of Computing Science and Engineering VIT University Vellore - 632014, Tamil Nadu, India

Journal of Artificial General Intelligence

This article is distributed under the terms of the Creative Commons Attribution Non-Commercial License, which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

{"article-title":"A Measure of Real-Time Intelligence"}

We propose a new measure of intelligence for general reinforcement learning agents, based on the notion that an agent’s environment can change at any step of...

A Measure of Real-Time Intelligence

Publicado en línea: 25 abr 2014

Páginas: 31 - 48

Recibido: 30 jun 2012

Aceptado: 25 nov 2013

DOI: https://doi.org/10.2478/jagi-2013-0003

Palabras clave
intelligence measure, reinforcement learning, real-time computation, algorithmic probability

© Vaibhav Gavane

This article is distributed under the terms of the Creative Commons Attribution Non-Commercial License, which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

A Measure of Real-Time Intelligence

Publicado en línea: 25 abr 2014

Páginas: 31 - 48

Recibido: 30 jun 2012

Aceptado: 25 nov 2013

DOI: https://doi.org/10.2478/jagi-2013-0003

Palabras claveintelligence measure, reinforcement learning, real-time computation, algorithmic probability

© Vaibhav Gavane

This article is distributed under the terms of the Creative Commons Attribution Non-Commercial License, which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Palabras clave
intelligence measure, reinforcement learning, real-time computation, algorithmic probability