Page - 209 - in Adaptive and Intelligent Temperature Control of Microwave Heating Systems with Multiple Sources

Bibliography [PR99] VassilisAPapavassiliouandStuartRussell.Conver- gence of reinforcement learning with general func- tionapproximators. In IJCAI,pages748–757,1999. [PS91] AH Pincombe and NF Smyth. Microwave heating of materials with low conductivity. Proceedings of theRoyalSocietyofLondon.SeriesA:Mathematicaland PhysicalSciences, 433(1889):479–498,1991. [PS06] Jan Peters and Stefan Schaal. Policy gradient meth- ods for robotics. In Intelligent Robots and Systems, 2006 IEEE/RSJ International Conference on, pages 2219–2225. IEEE,2006. [PS08a] Jan Peters and Stefan Schaal. Natural actor-critic. Neurocomputing, 71(7):1180–1190,2008. [PS08b] Jan Peters and Stefan Schaal. Reinforcement learn- ingofmotorskillswithpolicygradients. Neuralnet- works, 21(4):682–697,2008. [PSD01] Doina Precup, Richard S Sutton, and Sanjoy Das- gupta. Off-policytemporal-differencelearningwith function approximation. In ICML, pages 417–424, 2001. [PSRJG00] StephenPiche,BijanSayyar-Rodsari,DougJohnson, andMarkGerules. Nonlinearmodelpredictivecon- trol using neural networks. Control Systems, IEEE, 20(3):53–62,2000. [PVS05] Jan Peters, Sethu Vijayakumar, and Stefan Schaal. Natural actor-critic. In Machine Learning: ECML 2005,pages280–291.Springer,2005. [PW96] JingPengandRonaldJWilliams. Incrementalmulti- step Q-learning. Machine Learning, 22(1-3):283–290, 1996. [PW08] Yunpeng Pan and Jun Wang. Nonlinear model pre- dictive control using a recurrent neural network. In Neural Networks, 2008. IJCNN 2008.(IEEE World 209