- -

Evaluating a reinforcement learning algorithm with a general intelligence test

RiuNet: Repositorio Institucional de la Universidad Politécnica de Valencia

Compartir/Enviar a

Citas

Estadísticas

  • Estadisticas de Uso

Evaluating a reinforcement learning algorithm with a general intelligence test

Mostrar el registro sencillo del ítem

Ficheros en el ítem

Thumbnail
Nombre: caepia11-jho-jic- ...
Tamaño: 2.211Mb
Formato: PDF
Descripción: Versión del Autor.
Abrir
[Cerrado]
Nombre: fulltext.pdf
Tamaño: 611.0Kb
Formato: PDF
Descripción: Versión editorial
Solicitar una copia al autor
dc.contributor.author Insa Cabrera, Javier es_ES
dc.contributor.author Dowe, David L. es_ES
dc.contributor.author Hernández Orallo, José es_ES
dc.date.accessioned 2014-05-12T08:57:13Z
dc.date.issued 2011
dc.identifier.isbn 978-3-642-25273-0
dc.identifier.issn 0302-9743
dc.identifier.uri http://hdl.handle.net/10251/37392
dc.description.abstract In this paper we apply the recent notion of anytime universal intelligence tests to the evaluation of a popular reinforcement learning algorithm, Q-learning. We show that a general approach to intelligence evaluation of AI algorithms is feasible. This top-down (theory-derived) approach is based on a generation of environments under a Solomonoff universal distribution instead of using a pre-defined set of specific tasks, such as mazes, problem repositories, etc. This first application of a general intelligence test to a reinforcement learning algorithm brings us to the issue of task-specific vs. general AI agents. This, in turn, suggests new avenues for AI agent evaluation and AI competitions, and also conveys some further insights about the performance of specific algorithms. © 2011 Springer-Verlag. es_ES
dc.description.sponsorship We are grateful for the funding from the Spanish MEC and MICINN for projects TIN2009-06078-E/TIN, Consolider-Ingenio CSD2007-00022 and TIN2010-21062-C02, for MEC FPU grant AP2006-02323, and Generalitat Valenciana for Prometeo/2008/051. es_ES
dc.format.extent 11 es_ES
dc.language Inglés es_ES
dc.publisher Springer Verlag (Germany) es_ES
dc.relation.ispartof Advances in Artificial Intelligence es_ES
dc.relation.ispartofseries Lecture Notes in Computer Science;7023
dc.rights Reserva de todos los derechos es_ES
dc.subject AI algorithms es_ES
dc.subject General approach es_ES
dc.subject General intelligence tests es_ES
dc.subject Intelligence tests es_ES
dc.subject Q-learning es_ES
dc.subject Specific tasks es_ES
dc.subject Topdown es_ES
dc.subject Artificial intelligence es_ES
dc.subject Reinforcement es_ES
dc.subject Reinforcement learning es_ES
dc.subject Learning algorithms es_ES
dc.subject.classification LENGUAJES Y SISTEMAS INFORMATICOS es_ES
dc.title Evaluating a reinforcement learning algorithm with a general intelligence test es_ES
dc.type Capítulo de libro es_ES
dc.embargo.lift 10000-01-01
dc.embargo.terms forever es_ES
dc.identifier.doi 10.1007/978-3-642-25274-7_1
dc.relation.projectID info:eu-repo/grantAgreement/MICINN//TIN2009-06078-E/ES/ANYTIME UNIVERSAL INTELLIGENCE/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/MEC//CSD2007-00022/ES/Agreement Technologies/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/MICINN//TIN2010-21062-C02-02/ES/SWEETLOGICS-UPV/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/MEC//AP2006-0232/ES/AP2006-0232/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/Generalitat Valenciana//PROMETEO08%2F2008%2F051/ES/Advances on Agreement Technologies for Computational Entities (atforce)/ es_ES
dc.rights.accessRights Abierto es_ES
dc.contributor.affiliation Universitat Politècnica de València. Departamento de Sistemas Informáticos y Computación - Departament de Sistemes Informàtics i Computació es_ES
dc.description.bibliographicCitation Insa Cabrera, J.; Dowe, DL.; Hernández Orallo, J. (2011). Evaluating a reinforcement learning algorithm with a general intelligence test. En Advances in Artificial Intelligence. Springer Verlag (Germany). 7023:1-11. https://doi.org/10.1007/978-3-642-25274-7_1 es_ES
dc.description.accrualMethod S es_ES
dc.relation.conferencename 14th Conference of the Spanish Association for Artificial Intelligence, CAEPIA 2011 es_ES
dc.relation.conferencedate November 7-11, 2011 es_ES
dc.relation.conferenceplace La Laguna, Spain es_ES
dc.relation.publisherversion http://link.springer.com/chapter/10.1007/978-3-642-25274-7_1 es_ES
dc.description.upvformatpinicio 1 es_ES
dc.description.upvformatpfin 11 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.description.volume 7023 es_ES
dc.relation.senia 217838
dc.contributor.funder Ministerio de Educación y Ciencia es_ES
dc.contributor.funder Ministerio de Ciencia e Innovación es_ES
dc.contributor.funder Generalitat Valenciana es_ES
dc.description.references Dowe, D.L., Hajek, A.R.: A non-behavioural, computational extension to the Turing Test. In: Intl. Conf. on Computational Intelligence & multimedia applications (ICCIMA 1998), Gippsland, Australia, pp. 101–106 (1998) es_ES
dc.description.references Genesereth, M., Love, N., Pell, B.: General game playing: Overview of the AAAI competition. AI Magazine 26(2), 62 (2005) es_ES
dc.description.references Hernández-Orallo, J.: Beyond the Turing Test. J. Logic, Language & Information 9(4), 447–466 (2000) es_ES
dc.description.references Hernández-Orallo, J.: A (hopefully) non-biased universal environment class for measuring intelligence of biological and artificial systems. In: Hutter, M., et al. (eds.) 3rd Intl. Conf. on Artificial General Intelligence, Atlantis, pp. 182–183 (2010) es_ES
dc.description.references Hernández-Orallo, J.: On evaluating agent performance in a fixed period of time. In: Hutter, M., et al. (eds.) 3rd Intl. Conf. on Artificial General Intelligence, pp. 25–30. Atlantis Press (2010) es_ES
dc.description.references Hernández-Orallo, J., Dowe, D.L.: Measuring universal intelligence: Towards an anytime intelligence test. Artificial Intelligence 174(18), 1508–1539 (2010) es_ES
dc.description.references Legg, S., Hutter, M.: A universal measure of intelligence for artificial agents. Intl. Joint Conf. on Artificial Intelligence, IJCAI 19, 1509 (2005) es_ES
dc.description.references Legg, S., Hutter, M.: Universal intelligence: A definition of machine intelligence. Minds and Machines 17(4), 391–444 (2007) es_ES
dc.description.references Levin, L.A.: Universal sequential search problems. Problems of Information Transmission 9(3), 265–266 (1973) es_ES
dc.description.references Li, M., Vitányi, P.: An introduction to Kolmogorov complexity and its applications, 3rd edn. Springer-Verlag New York, Inc. (2008) es_ES
dc.description.references Sanghi, P., Dowe, D.L.: A computer program capable of passing IQ tests. In: Proc. 4th ICCS International Conference on Cognitive Science (ICCS 2003), Sydney, Australia, pp. 570–575 (2003) es_ES
dc.description.references Solomonoff, R.J.: A formal theory of inductive inference. Part I. Information and Control 7(1), 1–22 (1964) es_ES
dc.description.references Strehl, A.L., Li, L., Wiewiora, E., Langford, J., Littman, M.L.: PAC model-free reinforcement learning. In: Proc. of the 23rd Intl. Conf. on Machine Learning, ICML 2006, New York, pp. 881–888 (2006) es_ES
dc.description.references Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. The MIT press (1998) es_ES
dc.description.references Turing, A.M.: Computing machinery and intelligence. Mind 59, 433–460 (1950) es_ES
dc.description.references Veness, J., Ng, K.S., Hutter, M., Silver, D.: Reinforcement learning via AIXI approximation. In: Proc. 24th Conf. on Artificial Intelligence (AAAI 2010), pp. 605–611 (2010) es_ES
dc.description.references Watkins, C.J.C.H., Dayan, P.: Q-learning. Machine learning 8(3), 279–292 (1992) es_ES
dc.description.references Weyns, D., Parunak, H.V.D., Michel, F., Holvoet, T., Ferber, J.: Environments for multiagent systems state-of-the-art and research challenges. In: Weyns, D., Van Dyke Parunak, H., Michel, F. (eds.) E4MAS 2004. LNCS (LNAI), vol. 3374, pp. 1–47. Springer, Heidelberg (2005) es_ES
dc.description.references Whiteson, S., Tanner, B., White, A.: The Reinforcement Learning Competitions. The AI magazine 31(2), 81–94 (2010) es_ES
dc.description.references Woergoetter, F., Porr, B.: Reinforcement learning. Scholarpedia 3(3), 1448 (2008) es_ES
dc.description.references Zatuchna, Z., Bagnall, A.: Learning mazes with aliasing states: An LCS algorithm with associative perception. Adaptive Behavior 17(1), 28–57 (2009) es_ES


Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem