K.N. Toosi University of Technology International Journal of Robotics, Theory and Applications 2008-7144 7 1 2021 06 01 Fast Reinforcement Learning approach to robust optimal control of bipedal robots with Point-feet 165704 EN Majid Anjidani PhD student, Iran University of Science and Technology, Tehran, Iran Mohammad Reza Jahed Motlagh Faculty member of computer department, Iran University of Science and Technology, Tehran, Iran Mahmood Fathy Faculty member of computer dep., Iran University of Science and Technology, Tehran, Iran Majid Nili Ahmadabad Faculty member of Electrical and Computer Department, University of Tehran, Tehran, Iran Journal Article 2016 12 11 Designing a walking gait for biped robots, that can preserve stability against a known range of disturbances, is very important in real applications. In the area of biped robots with point-feet, designing an exponentially stable walking gait with desired features has been recently done by an online reinforcement learning method called PI^2-WG. However, the designed gait might not be robust enough against disturbances. Therefore, we extend a robust version of PI^2-WG to design an exponentially stable walking gait which is robust against modeling errors/disturbances and we call it R-SPI^2-WG. It is done by minimizing the costs of worst rollouts which are generated in presence of different modeling errors/disturbances. We study the ability of the proposed method to adapt the controller of RABBIT, which is a planar biped robot with point-feet, for some robust applications. The simulation results show that the designed gaits are exponentially stable and robust against modeling errors/disturbances in a feasible range.