Exploring Constrained Reinforcement Learning Algorithms for Quadrupedal Locomotion

Open access
Autor(in)
Alle anzeigen
Datum
2024Typ
- Conference Paper
ETH Bibliographie
yes
Altmetrics
Abstract
Shifting from traditional control strategies to Deep Reinforcement Learning (RL) for legged robots poses inherent challenges, especially when addressing real-world physical con straints during training. While high-fidelity simulations provide significant benefits, they often bypass these essential physical limitations. In this paper, we experiment with the Constrained Markov Decision Process (CMDP) framework instead of the conventional unconstrained RL for robotic applications. We evaluated five constrained policy optimization algorithms for quadrupedal locomotion using three different robot models. Our aim is to evaluate their applicability in real-world sce narios. Our robot experiments demonstrate the critical role of incorporating physical constraints, yielding successful sim-to-real transfers, and reducing operational errors on physical systems. The CMDP formulation streamlines the training process by separately handling constraints from rewards. Our findings underscore the potential of constrained RL for the effective development and deployment of learned controllers in robotics. Mehr anzeigen
Persistenter Link
https://doi.org/10.3929/ethz-b-000703818Publikationsstatus
publishedExterne Links
Buchtitel
2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)Seiten / Artikelnummer
Verlag
IEEEKonferenz
Organisationseinheit
09570 - Hutter, Marco / Hutter, Marco
Förderung
852044 - Learning Mobility for Real Legged Robots (EC)
ETH Bibliographie
yes
Altmetrics