| 1 | \begin{thebibliography}{10} |
|---|
| 2 | \providecommand{\url}[1]{\texttt{#1}} |
|---|
| 3 | \providecommand{\urlprefix}{URL } |
|---|
| 4 | \expandafter\ifx\csname urlstyle\endcsname\relax |
|---|
| 5 | \providecommand{\doi}[1]{doi:\discretionary{}{}{}#1}\else |
|---|
| 6 | \providecommand{\doi}{doi:\discretionary{}{}{}\begingroup |
|---|
| 7 | \urlstyle{rm}\Url}\fi |
|---|
| 8 | \providecommand{\selectlanguage}[1]{\relax} |
|---|
| 9 | \providecommand{\eprint}[2][]{\url{#2}} |
|---|
| 10 | |
|---|
| 11 | \bibitem{7_lq_methods} |
|---|
| 12 | Anderson, M.~J., B.D.O.: Optimal Control - Linear Quadratic Methods. |
|---|
| 13 | \emph{Prentice Hall, Englewood Cliffs, NJ}, 1990. |
|---|
| 14 | |
|---|
| 15 | \bibitem{dynamic_programming} |
|---|
| 16 | Bellman, R.: Dynamic programming. \emph{Princeton University Press}, 1957. |
|---|
| 17 | |
|---|
| 18 | \bibitem{2_int_a_in_dec} |
|---|
| 19 | Ferreira, E.; Subrahmanian, E.; Manstetten, D.: Intelligent agents in |
|---|
| 20 | decentralized traffic control. \emph{Intelligent Transportation Systems}, |
|---|
| 21 | 2001. |
|---|
| 22 | |
|---|
| 23 | \bibitem{4_rmm_formalization} |
|---|
| 24 | Gmytrasiewicz, P.~J.; Durfee, E.~H.: A rigorous, operational formalization of |
|---|
| 25 | recursive modeling. \emph{First International Conference on Multiagent |
|---|
| 26 | Systems}, 1995. |
|---|
| 27 | |
|---|
| 28 | \bibitem{5_bayes_learn} |
|---|
| 29 | Nagy, I.; Nedoma, P.; Ettler, P.; aj.: O bayesovsk{\'e}m u\v{c}en{\'i}. |
|---|
| 30 | \emph{Automa}, 2002. |
|---|
| 31 | |
|---|
| 32 | \bibitem{1_rmm_bayes_learning} |
|---|
| 33 | Ou, H.; Zhang, W.; Xu, X.: Urban traffic multi-agent system based on RMM and |
|---|
| 34 | Bayesian learning. \emph{American Control Conference}, 2002. |
|---|
| 35 | |
|---|
| 36 | \bibitem{17_fronta} |
|---|
| 37 | P., P.; J., D.; Fl{\'i}dr: Modelling and Simultaneous Estimation of State and |
|---|
| 38 | Parameters of Traffic System. \emph{Robotics, Automation and Control}, 2008. |
|---|
| 39 | |
|---|
| 40 | \bibitem{learning_to_predict} |
|---|
| 41 | Sutton, R.~S.: Learning to predict by the methods of temporal didffrences. |
|---|
| 42 | \emph{Machine Learning}, 1988. |
|---|
| 43 | |
|---|
| 44 | \bibitem{tlc_using_sarsa} |
|---|
| 45 | Thorpe, T.: Vehicle traffic light controlusing sarsa. \emph{Master’s thesis, |
|---|
| 46 | Department of Computer Science, Colorado State University}, 1997. |
|---|
| 47 | |
|---|
| 48 | \bibitem{6_tuc_lq} |
|---|
| 49 | Vaya~Dinopoulou, M.~P., Christina~Diakaki: Applications of the urban traffic |
|---|
| 50 | control strategy TUC. \emph{European Journal of Operational Research}, 2005. |
|---|
| 51 | |
|---|
| 52 | \bibitem{leraning_from_delayed_rewards} |
|---|
| 53 | Watkins, C. J. C.~H.: Leraning from Delayed Rewards. \emph{PhD thesis, King's |
|---|
| 54 | College, Cambridge, England}, 1989. |
|---|
| 55 | |
|---|
| 56 | \bibitem{q_learning} |
|---|
| 57 | Watkins, C. J. C.~H.; Dayan, P.: Q-leraning. \emph{Machine Learning}, 1992. |
|---|
| 58 | |
|---|
| 59 | \bibitem{3_i_traff_light_c} |
|---|
| 60 | Wiering, M.; {Van Veenen}, J.; Vreeken, J.; aj.: Intelligent traffic light |
|---|
| 61 | control. \emph{European Research Consortium for Informatics and Mathematics}, |
|---|
| 62 | 2003. |
|---|
| 63 | |
|---|
| 64 | \bibitem{wooldridge} |
|---|
| 65 | Wooldridge, M.: \emph{Multi Agent Systems}. MIT Press, Březen 2005. |
|---|
| 66 | |
|---|
| 67 | \end{thebibliography} |
|---|
