HYDRA: Hybrid Robot Actions for Imitation Learning

Suneel Belkhale, Yuchen Cui, Dorsa Sadigh

Keywords: Imitation Learning, Robotics, Manipulation

TL;DR: We learn a hybrid robot action space that dynamically switches between low-level actions and high-level waypoints, and our method substantially outperforms baselines on a variety of long horizon real world tasks like making coffee and sorting dishes.

Abstract: Imitation Learning (IL) is a sample efficient paradigm for robot learning using expert demonstrations. However, policies learned through IL suffer from state distribution shift at test time, due to compounding errors in action prediction which lead to previously unseen states. Choosing an action representation for the policy that minimizes this distribution shift is critical in imitation learning. Prior work propose using temporal action abstractions to reduce compounding errors, but they often sacrifice policy dexterity or require domain-specific knowledge. To address these trade-offs, we introduce HYDRA, a method that leverages a hybrid action space with two levels of action abstractions: sparse high-level waypoints and dense low-level actions. HYDRA dynamically switches between action abstractions at test time to enable both coarse and fine-grained control of a robot. In addition, HYDRA employs action relabeling to increase the consistency of actions in the dataset, further reducing distribution shift. HYDRA outperforms prior imitation learning methods by 30-40% on seven challenging simulation and real world environments, involving long-horizon tasks in the real world like making coffee and toasting bread. Videos are found on our website: https://tinyurl.com/3mc6793z

Student First Author: yes

Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)

Website: https://sites.google.com/corp/view/hydra-il-2023

Video: https://sites.google.com/corp/view/hydra-il-2023

Code: https://sites.google.com/corp/view/hydra-il-2023