End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representation

no code implementations • 12 Feb 2022 • Tianying Wang, En Yen Puang, Marcus Lee, Yan Wu, Wei Jing

The proposed method learns keypoints from camera images as the state representation, through a self-supervised autoencoder architecture.

reinforcement-learning Reinforcement Learning (RL)