Abstract
Combining deep neural networks with reinforcement learning has shown great potential in the next-generation intelligent control. However, there are challenges in terms of safety and cost in practical applications. In this paper, we propose the Intervention Aided Reinforcement Learning (IARL) framework, which utilizes human intervened robot-environment interaction to improve the policy. We used the Unmanned Aerial Vehicle (UAV) as the test platform. We built neural networks as our policy to map sensor readings to control signals on the UAV. Our experiment scenarios cover both simulation and reality. We show that our approach substantially reduces the human intervention and improves the performance in autonomous navigation, at the same time it ensures safety and keeps training cost acceptable. © CoRL 2018. All rights reserved.
| Original language | English |
|---|---|
| Pages (from-to) | 410-421 |
| Journal | Proceedings of Machine Learning Research |
| Volume | 87 |
| Publication status | Published - 2018 |
| Event | 2nd Conference on Robot Learning, CoRL 2018 - Zurich, Switzerland Duration: 29 Oct 2018 → 31 Oct 2018 https://proceedings.mlr.press/v87/ |
Bibliographical note
Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].Research Keywords
- Imitation Learning
- Reinforcement Learning
- Visual Navigation
Fingerprint
Dive into the research topics of 'Intervention Aided Reinforcement Learning for Safe and Practical Policy Optimization in Navigation'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver