Real-Time Learning of Efficient Lift Generation on a Dynamically Scaled Flapping Wing 
This work presents a successful application of a policy search algorithm to a real-time robotic learning problem, where the goal is to maximize the efficiency of lift generation on a dynamically scaled flapping robotic wing. Learning is performed for different prescribed stroke amplitudes to find the optimal wing pitching amplitude and the stroke-pitch phase difference that maximize lift generation's power loading (PL), a measure of aerodynamic efficiency.
Publication on ieeexplore.ieee.org