Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play

Collecting Human Demonstrations in a Virtual Reality Environment

Model-Based Land-Ball Skill

Land-Ball Skill Using Forward and Inverse Dynamics Models

Land-Ball Skill Using Forward and Inverse Dynamics Models with Cross-Entropy Method (CEM)

Strategy over Strikes Demonstrated by Humans

Cooperative Strategy Using Land-Ball Skill

Adversarial Strategy Using Land-Ball Skill

Strategy over Arbitrary Strikes

Cooperative Strategy Using Arbitrary Strikes from the Hit-Ball Skill

Adversarial Strategy Using Arbitrary Strikes from the Hit-Ball Skill

Strategy over Low-Level Joint Control