Article ; Online: Multimodal information bottleneck for deep reinforcement learning with multiple sensors.
Neural networks : the official journal of the International Neural Network Society
2024 Volume 176, Page(s) 106347
Abstract: Reinforcement learning has achieved promising results on robotic control tasks but struggles to leverage information effectively from multiple sensory modalities that differ in many characteristics. Recent works construct auxiliary losses based on ... ...
| Abstract | Reinforcement learning has achieved promising results on robotic control tasks but struggles to leverage information effectively from multiple sensory modalities that differ in many characteristics. Recent works construct auxiliary losses based on reconstruction or mutual information to extract joint representations from multiple sensory inputs to improve the sample efficiency and performance of reinforcement learning algorithms. However, the representations learned by these methods could capture information irrelevant to learning a policy and may degrade the performance. We argue that compressing information in the learned joint representations about raw multimodal observations is helpful, and propose a multimodal information bottleneck model to learn task-relevant joint representations from egocentric images and proprioception. Our model compresses and retains the predictive information in multimodal observations for learning a compressed joint representation, which fuses complementary information from visual and proprioceptive feedback and meanwhile filters out task-irrelevant information in raw multimodal observations. We propose to minimize the upper bound of our multimodal information bottleneck objective for computationally tractable optimization. Experimental evaluations on several challenging locomotion tasks with egocentric images and proprioception show that our method achieves better sample efficiency and zero-shot robustness to unseen white noise than leading baselines. We also empirically demonstrate that leveraging information from egocentric images and proprioception is more helpful for learning policies on locomotion tasks than solely using one single modality. |
|---|---|
| Language | English |
| Publishing date | 2024-04-27 |
| Publishing country | United States |
| Document type | Journal Article |
| ZDB-ID | 740542-x |
| ISSN | 1879-2782 ; 0893-6080 |
| ISSN (online) | 1879-2782 |
| ISSN | 0893-6080 |
| DOI | 10.1016/j.neunet.2024.106347 |
| Database | MEDical Literature Analysis and Retrieval System OnLINE |
More links
Kategorien
In stock of ZB MED Cologne/Königswinter
| Zs.A 2365: Show issues | Location: Je nach Verfügbarkeit (siehe Angabe bei Bestand) bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular Jg. 1995 - 2021: Lesesall (2.OG) ab Jg. 2022: Lesesaal (EG) |
Order via subito
This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.