Recursive least-squares temporal difference algorithm is deduced, which can use data more efficiently with fast convergence and less computational burden. Reinforcement learning based on recursive least-squares methods is applied to ship steering control, as provides an efficient way for the improvement of ship steering control performance. It removes the defect that the conventional intelligent algorithm learning must be provided with some sample data. The parameters of controller are on-line learned and adjusted. Simulation results show that the ship course can be properly controlled in case of the disturbances of wave, wind, current. It is demonstrated that the proposed algorithm is a promising alternative to conventional autopilots.
Reinforcement learning control for ship steering using recursive least-squares algorithm
Verstärkend lernende Regelung mit einem rekursiven Algorithmus der kleinsten Quadrate für die Schiffslenkung
2005
6 Seiten, 6 Bilder, 8 Quellen
Aufsatz (Konferenz)
Englisch
Recursive Least-Squares Filtering
AIAA | 2015
|Recursive Least-Squares Filtering
AIAA | 2009
|Recursive Least-Squares Filtering
AIAA | 2005
|Robust recursive least squares algorithm for automotive suspension identification
SAE Technical Papers | 2005
|