The source code used to construct an Online Reinforcement Learning Agent for Flight Control of a Cessna Citation 550 aircraft. The full thesis can be downloaded on http://resolver.tudelft.nl/uuid:38547b1d-0535-4b30-a348-67ac40c7ddcc. The thesis contains a scientific paper with a consize description on the implemented agent design.
For a complete list of references see the thesis report. This work is primarily based on: 1: Zhou, Y., van Kampen, E., Chu, Q.P., "Incremental model based online dual heuristic programming for nonlinear adaptive control", Control Engineering Practice, Vol. 73, 2018, pp. 13–25 2: Ferrari, S., Stengel, R.F., "Online adaptive critic flight control", Journal of Guidance, Control, and Dynamics, Vol. 27, No. 5, 2004, pp. 777–786.