The Nguyen, H. and Bui, L.T. and Garratt, M. and Abbass, H. (2018) Apprenticeship bootstrapping: Inverse Reinforcement learning in a multi-skill UAV-UGV coordination task. In: 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018, 10 July 2018 through 15 July 2018.
Full text not available from this repository. (Upload)Abstract
Apprenticeship learning enables learning from human demonstrations performed on tasks. However, acquiring demonstrations in complex tasks where a human expert is not available can be a challenge. In this paper, we propose a new learning algorithm, called Apprenticeship bootstrapping via Inverse Reinforcement Learning using Deep Q-learning (ABS via IRL-DQN), to learn a complex task through using demonstrations performed on primitive sub-tasks. The algorithm is evaluated on an aerial and ground coordination scenario, where an Unmanned Aerial Vehicle (UAV) is required to maintain three Unmanned Ground Vehicles (UGVs) within a field of view of the UAV's camera (FoV). The results show that performance of our proposed algorithm is comparable to that of a human, and competitive to the original IRL using expert demonstrations performed on the composite task. © 2018 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Divisions: | Faculties > Faculty of Information Technology |
Uncontrolled Keywords: | Antennas; Apprentices; Autonomous agents; Deep learning; Demonstrations; Ground vehicles; Intelligent vehicle highway systems; Learning algorithms; Multi agent systems; Unmanned aerial vehicles (UAV); Apprenticeship learning; Ground-air interaction; Inverse reinforcement learning; Q-learning; UGVs; Reinforcement learning |
Additional Information: | Conference code: 139890. Language of original document: English. |
URI: | http://eprints.lqdtu.edu.vn/id/eprint/9618 |