Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on androids is now availab le. According to news reporting from Saga, Japan, by NewsRx journalists, researc h stated, "In this paper, a novel reinforcement learning method that enables a h umanoid robot to learn bipedal walking using a simple reference motion is propos ed." Funders for this research include Japan Society For The Promotion of Science. The news correspondents obtained a quote from the research from Saga University: "Reinforcement learning has recently emerged as a useful method for robots to l earn bipedal walking, but, in many studies, a reference motion is necessary for successful learning, and it is laborious or costly to prepare a reference motion . To overcome this problem, our proposed method uses a simple reference motion c onsisting of three sine waves and automatically sets the waveform parameters usi ng Bayesian optimization. Thus, the reference motion can easily be prepared with minimal human involvement. Moreover, we introduce two means to facilitate reinf orcement learning: (1) we combine reinforcement learning with inverse kinematics (IK), and (2) we use the reference motion as a bias for the action determined v ia reinforcement learning, rather than as an imitation target."
NETL
NSTL