Reward Shaping to Learn Natural Object Manipulation With an Anthropomorphic Robotic Hand and Hand Pose Priors via On-Policy Reinforcement Learning

Conference Object

Abstract: A key challenge in reinforcement learning (RL) for robot manipulation is to provide a reward functio

Palabras claves:

Anthropomorphic robotic hand, Deep reinforcement learning, Hand Poses Priors, object manipulation

Autores:

Edwin Valarezo Anazco, Jeong J.G., Jung H., Kim T.S., Lee J.H., Oh J., Rivera P., Ryu G.

Fuentes:

google

scopus