In this study, we propose a multitask reinforcement learning algorithm for foundational policy acquisition to generate novel motor skills. Inspired by human sensorimotor adaptation mechanisms, we aim to train encoder-decoder networks that can be commonly used to learn novel motor skills in a single movement category. To train the policy network, we develop the multitask reinforcement learning method, where the policy needs to cope with changes in goals or environments with different reward functions or physical parameters of the environment in dynamic movement generation tasks. Here, as a concrete task, we evaluated the proposed method with the ball heading task using a monopod robot model. The results showed that the proposed method could adapt to novel target positions or inexperienced ball restitution coefficients. Furthermore, we demonstrated that the acquired foundational policy network originally learned for heading motion, can be used to generate an entirely new overhead kicking skill.
翻译:暂无翻译