Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2019
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912161542963200 |
|---|---|
| author | Liu, Boyi Wang, Lujia Liu, Ming |
| author_facet | Liu, Boyi Wang, Lujia Liu, Ming |
| contents | This paper was motivated by the problem of how to make robots fuse and transfer their experience so that they can effectively use prior knowledge and quickly adapt to new environments. To address the problem, we present a learning architecture for navigation in cloud robotic systems: Lifelong Federated Reinforcement Learning (LFRL). In the work, We propose a knowledge fusion algorithm for upgrading a shared model deployed on the cloud. Then, effective transfer learning methods in LFRL are introduced. LFRL is consistent with human cognitive science and fits well in cloud robotic systems. Experiments show that LFRL greatly improves the efficiency of reinforcement learning for robot navigation. The cloud robotic system deployment also shows that LFRL is capable of fusing prior knowledge. In addition, we release a cloud robotic navigation-learning website based on LFRL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1901_06455 |
| institution | arXiv |
| publishDate | 2019 |
| record_format | arxiv |
| spellingShingle | Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems Liu, Boyi Wang, Lujia Liu, Ming Robotics Artificial Intelligence Distributed, Parallel, and Cluster Computing Machine Learning Systems and Control This paper was motivated by the problem of how to make robots fuse and transfer their experience so that they can effectively use prior knowledge and quickly adapt to new environments. To address the problem, we present a learning architecture for navigation in cloud robotic systems: Lifelong Federated Reinforcement Learning (LFRL). In the work, We propose a knowledge fusion algorithm for upgrading a shared model deployed on the cloud. Then, effective transfer learning methods in LFRL are introduced. LFRL is consistent with human cognitive science and fits well in cloud robotic systems. Experiments show that LFRL greatly improves the efficiency of reinforcement learning for robot navigation. The cloud robotic system deployment also shows that LFRL is capable of fusing prior knowledge. In addition, we release a cloud robotic navigation-learning website based on LFRL. |
| title | Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems |
| topic | Robotics Artificial Intelligence Distributed, Parallel, and Cluster Computing Machine Learning Systems and Control |
| url | https://arxiv.org/abs/1901.06455 |