Tytuł artykułu
Autorzy
Wybrane pełne teksty z tego czasopisma
Identyfikatory
Warianty tytułu
Języki publikacji
Abstrakty
The article analyses a reinforcement learning method in which the subject of learning is defined. The essence of this method is the selection of activities by a try and fail process and awarding deferred rewards. Theoretical analyses were supplemented by the practical studies, with reference to implementation of the Sarsa( Lambda) algorithm, with replacing eligibility traces and the Epsilon greedy policy.
Słowa kluczowe
Czasopismo
Rocznik
Tom
Strony
61--76
Opis fizyczny
Bibliogr. 8 poz.
Twórcy
autor
- Departament of Electrical Engineering, University of Montenegro, Cetinjski put bb, Podgorica, Yugoslavia, jaroslav@Server1.cis.cg.ac.yu
Bibliografia
- [1] Boyan J. A., Littman, M. L.: Packet Routing in Dynamically Changing Networks: A Reinforcement Learning Approach, Advances in Neural Information Processing Systems: Proceedings of the 994 Conference, San Francisco, CA, USA, 1994.
- [2] Doya K.; Reinforcement Learning in Continuous Time and Space, Neural Computation, 2000, Vol 12, No. 1, pp. 219-246.
- [3] Kaelbling L. P., Littman M. L., Moore A. W.: Reinforcement Learning: A Survey, Journal of Artificial Intelligence, 1996,. Vol. 4, pp. 237-285.
- [4] Lewis M. E., Puterman M. L. A.: Probabilistic Analysis of Bias Optimality in Unichain Markov Decision Process, IEEE Transactions on Automatic Control, 2001, Vol. 46, No. l,pp. 96-101.
- [5] Poliscuk J. E.: A contribution to methodology of development of Decision Support Systems and Expert Systems, Doctors Thesis, Faculty of Organization and Informatics, University of Zagreb, Croatia, 1992.
- [6] Rolls E. T., Milward T„ Wiskott L.: A Model of Invoviant Object Recognition in the Visual System: Learning Rules, Activation Functions, Lateral Inhibition, and Information - Based Performance Measures, Neural Computation, 2000, Vol. 2, No. 11, pp. 2547-2573.
- [7] Sutton R. S., Barto A. G.: Reinforcement Learning: An Introduction, MIT press - Bradford Books, Cambridge, MA, USA, 1998.
- [8] Szepesvari C., Littman M. L. A.: Unified Analysis of Value - Function - Based Reinforcement - Learning Algorithms, Neural Computation, 1999, Vol 11, No. 8, pp. 2017-2061.
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-article-LOD7-0027-0088