论文信息 - Synthesis of reinforcement learning, neural networks and PI control applied to a simulated heating coil - 字舞流文

Synthesis of reinforcement learning, neural networks and PI control applied to a simulated heating coil

Douglas C. Hittle | Charles W. Anderson | Alon D. Katz | R. Matthew Kretchmar | R. M. Kretchmar | C. Anderson | D. Hittle | Alon D. Katz

[1] J. F. Kreider,et al. Neural networks applied to buildings -- A tutorial and case studies in prediction and adaptive control , 1996 .

[2] C. E. Dorgan,et al. Optimizing system control with load prediction by neural networks for an ice-storage system , 1996 .

[3] Ben J. A. Kröse,et al. Learning from delayed rewards , 1995, Robotics Auton. Syst..

[4] A. L. Dexter,et al. Neural control of non-linear HVAC plant , 1994, 1994 Proceedings of IEEE International Conference on Control and Applications.

[5] C. Anderson,et al. Multigrid Q-Learning , 1994 .

[6] Charles W. Anderson,et al. Q-Learning with Hidden-Unit Restarting , 1992, NIPS.

[7] M. Gabriel,et al. Learning and Computational Neuroscience: Foundations of Adaptive Networks , 1990 .

[8] Richard S. Sutton,et al. Learning and Sequential Decision Making , 1989 .