Adapting to the “Open World”: The Utility of Hybrid Hierarchical Reinforcement Learning and Symbolic Planning

Pierrick Lorang, Helmut Horvath, Tobias Kietreiber, Patrik Zips, Clemens Heitzinger, Matthias Scheutz

Publikation: Beitrag in Buch oder TagungsbandVortrag mit Beitrag in TagungsbandBegutachtung

Abstract

Open-world robotic tasks such as autonomous driving pose significant challenges to robot control due to unknown and unpredictable events that disrupt task performance. Neural network-based reinforcement learning (RL) techniques (like DQN, PPO, SAC, etc.) struggle to adapt in large domains and suffer from catastrophic forgetting. Hybrid planning and RL approaches have shown some promise in handling environmental changes but lack efficiency in accommodation speed. To address this limitation, we propose an enhanced hybrid system with a nested hierarchical action abstraction that can utilize previously acquired skills to effectively tackle unexpected novelties. We show that it can adapt faster and generalize better compared to state-of-the-art RL and hybrid approaches, significantly improving robustness when multiple environmental changes occur at the same time.
OriginalspracheEnglisch
Titel 2024 IEEE International Conference on Robotics and Automation (ICRA)
Seiten508-514
DOIs
PublikationsstatusVeröffentlicht - 8 Aug. 2024
VeranstaltungIEEE International Conference on Robotics and Automation - Yokohama, Japan
Dauer: 13 Mai 202417 Mai 2024
https://2024.ieee-icra.org/

Publikationsreihe

Name2024 IEEE International Conference on Robotics and Automation (ICRA)

Konferenz

KonferenzIEEE International Conference on Robotics and Automation
KurztitelICRA
Land/GebietJapan
StadtYokohama
Zeitraum13/05/2417/05/24
Internetadresse

Research Field

  • Complex Dynamical Systems

Diese Publikation zitieren