Metadata only
Date
2024-07Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
Reinforcement learning algorithms typically consider discrete-time dynamics, even though the underlying systems are often continuous in time. In this paper, we introduce a model-based reinforcement learning algorithm that represents continuous-time dynamics using nonlinear ordinary differential equations (ODEs). We capture epistemic uncertainty using well-calibrated probabilistic models, and use the optimistic principle for exploration. Our regret bounds surface the importance of the measurement selection strategy (MSS), since in continuous time we not only must decide how to explore, but also when to observe the underlying system. Our analysis demonstrates that the regret is sublinear when modeling ODEs with Gaussian Processes (GP) for common choices of MSS, such as equidistant sampling. Additionally, we propose an adaptive, data-dependent, practical MSS that, when combined with GP dynamics, also achieves sublinear regret with significantly fewer samples. We showcase the benefits of continuous-time modeling over its discrete-time counterpart, as well as our proposed adaptive MSS over standard baselines, on several applications. Show more
Publication status
publishedExternal links
Book title
Advances in Neural Information Processing Systems 36Pages / Article No.
Publisher
CurranEvent
Organisational unit
03908 - Krause, Andreas / Krause, Andreas
Funding
180545 - NCCR Automation (phase I) (SNF)
Related publications and datasets
Is new version of: https://openreview.net/forum?id=VkhvDfY2dB
Notes
Poster presentation on December 13, 2023.More
Show all metadata
ETH Bibliography
yes
Altmetrics