DeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning

This paper from The University of British Columbia students Xue Bin Peng, Glen Berseth, Kangkang Yin & Michiel van de Panne shows a character learning locomtion via predictive footsteps, while performing complex tasks such as dribbling a ball.

Learning physics-based locomotion skills is a difficult problem, leading to solutions that typically exploit prior knowledge of various forms. In this paper we aim to learn a variety of environment-aware locomotion skills with a limited amount of prior knowledge…

Read the paper here.