Smooth and Efficient Policy Exploration for Robot Trajectory Learning

1 code implementation • 13 Apr 2018 • Shidi Li, Chee-Meng Chew, Velusamy Subramaniam

Many policy search algorithms have been proposed for robot learning and proved to be practical in real robot applications.

Robotics

PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Point Atrous Convolution for Unorganized 3D Points

1 code implementation • 23 Jul 2019 • Liang Pan, Chee-Meng Chew, Gim Hee Lee

Motivated by the success of encoding multi-scale contextual information for image analysis, we propose our PointAtrousGraph (PAG) - a deep permutation-invariant hierarchical encoder-decoder for efficiently exploiting multi-scale edge features in point clouds.

A Versatile Agent for Fast Learning from Human Instructors

no code implementations • 1 Mar 2022 • YiWen Chen, Zedong Zhang, Haofeng Liu, Jiayi Tan, Chee-Meng Chew, Marcelo Ang

In recent years, a myriad of superlative works on intelligent robotics policies have been done, thanks to advances in machine learning.

Hierarchical Reinforcement Learning Imitation Learning +1