Iterative Reinforcement Learning Based Design of Dynamic Locomotion Skills for Cassie
arXiv: Robotics, 2019.
Deep reinforcement learning (DRL) is a promising approach for developing legged locomotion skills. However, the iterative design process that is inevitable in practice is poorly supported by the default methodology. It is difficult to predict the outcomes of changes made to the reward functions, policy architectures, and the set of tasks ...More
PPT (Upload PPT)