Autonomous navigation of an over-actuated marine platform using reinforcement learning
Konstantinos Tziortziotis, Nikolaos Tziortziotis, Kostas I. Vlachos, Konstantinos Blekas · 2016
This paper investigates the use of reinforcement learning for the navigation of an over-actuated marine platform in unknown environments. The proposed approach uses an online least-squared policy iteration scheme for value function approximation in order to estimate optimal policy. We evaluate our approach in a simulation platform and report some initial results concerning its performance on estimating optimal navigation policies to unknown environments under different environmental disturbances. The results are promising.