Autonomous micro-helicopter control based on reinforcement learning with replacing eligibility traces

Concerns the development of a micro-helicopter using MEMS. For its overall size, the micro helicopter could not equip with strong sensors and MPU, which affects the helicopter to get the whole environment information, therefore, the traditional control method disagrees with the helicopter with the uncertain environment. However, the method based on behavior only uses trial and error without the exact model of the environment. We adopt reinforcement learning with replacing eligibility traces integrating the temporal difference learning, which improve the efficiency and speed convergence. The results of simulation prove the validity of the learning algorithms. At last, the paper introduces the existent problems with the helicopter control and gives the future study.