[2F6-OS-16b] 知識・学習の転移可能性～ヒトとＡＩ～(2/2)

[2F6-OS-16b-03] Toward curriculum learning for articulated control in throwing tasks

〇Ryunosuke Tazawa¹, Takuma Torii¹, Shohei Hidaka¹ (1. Japan Advanced Institute of Science and Technology)

Keywords:Motor control, Articulated controller, Throwing tasks, Transfer learning, Curriculum learning

High-dimensional systems such as a double pendulum are difficult to control optimally due to the large number of degrees of freedom. Curriculum learning is one of the effective learning systems. It is a way to start to learn for simple task and gradually shift to a more complex task, which is an effective strategy for complex ones. In this research, we proposed a curriculum for an efficient reinforcement learning method by discovering the optimum learning initial value through a throwing task simulation.