Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations
Jun 30, 2022
Reinforcement Learning for Robotics
My research interests focus on the general field of robot learning, including reinforcement learning, developmental robotics and legged intelligence.
In this work, we propose a generative adversarial method for inferring reward functions from partial and potentially physically incompatible demonstrations for successful skill acquirement where reference or expert demonstrations are not easily accessible.
Chenhao Li, Marin Vlastelica, Sebastian Blaes, Jonas Frey, Felix Grimminger, Georg Martius
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
Methods that allow skill transfer from limited and noisy reference demonstrations.
Dec 2, 2022 5:00 PM Machines in Motion Laboratory, New York University
A method for inferring imitation signals from poor expert demonstrations.
Aug 10, 2022 3:00 PM Robotic Systems Lab, ETH Zurich