Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions

Sep 15, 2022
Go to Project Site
System Overview
Featured Robotics Reinforcement Learning
Chenhao Li
Chenhao Li
Reinforcement Learning for Robotics

My research interests focus on the general field of robot learning, including reinforcement learning, developmental robotics and legged intelligence.

Publications

Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions
In this work, we propose a cooperative generative adversarial method for obtaining controllable skill sets from unlabeled datasets containing diverse state transition patterns.
Chenhao Li, Sebastian Blaes, Pavel Kolev, Marin Vlastelica, Jonas Frey, Georg Martius
PDF Cite Code Project Poster Video
Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions

Events

Developmental Legged Intelligence: from Imitation to Generation
Popular methods that enable robot learning from limited demonstrations.
Mar 5, 2024 4:00 PM AI4CE Lab, New York University
Project Project Project
Developmental Legged Intelligence: from Imitation to Generation
Learning from Limited Demonstrations: Lessons We have Learned
Popular methods that enable robot learning from limited demonstrations.
Nov 15, 2023 11:00 AM Learning & Adaptive Systems Group, ETH Zurich
Project Project Project
Learning from Limited Demonstrations: Lessons We have Learned
Reducing Human Efforts in Reinforcement Learning for Legged Skill Development
Works that propose possible solutions to reduce such human involvement, specifically with examples of legged skill development using model-free reinforcement learning and imitation learning methods.
Jan 12, 2023 4:00 PM Biomimetic Robotics Lab, Massachusetts Institute of Technology
Project Project Project
Reducing Human Efforts in Reinforcement Learning for Legged Skill Development
Reducing Human Efforts for Expert Acquisition in Imitation Learning
Methods that allow skill transfer from limited and noisy reference demonstrations.
Dec 2, 2022 5:00 PM Machines in Motion Laboratory, New York University
Project Project
Reducing Human Efforts for Expert Acquisition in Imitation Learning