Intervention Aided Reinforcement Learning for Safe and Practical Policy Optimization in Navigation

Fan Wang, Bo Zhou, Ke Chen, Tingxiang Fan, Xi Zhang, Jiangyong Li, Hao Tian, Jia Pan
; Proceedings of The 2nd Conference on Robot Learning, PMLR 87:410-421, 2018.

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 pa- per, 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 navigation1, at the same time it ensures safety and keeps training cost acceptable.

Cite this Paper


BibTeX
@InProceedings{pmlr-v87-wang18a, title = {Intervention Aided Reinforcement Learning for Safe and Practical Policy Optimization in Navigation}, author = {Wang, Fan and Zhou, Bo and Chen, Ke and Fan, Tingxiang and Zhang, Xi and Li, Jiangyong and Tian, Hao and Pan, Jia}, booktitle = {Proceedings of The 2nd Conference on Robot Learning}, pages = {410--421}, year = {2018}, editor = {Aude Billard and Anca Dragan and Jan Peters and Jun Morimoto}, volume = {87}, series = {Proceedings of Machine Learning Research}, address = {}, month = {29--31 Oct}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v87/wang18a/wang18a.pdf}, url = {http://proceedings.mlr.press/v87/wang18a.html}, 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 pa- per, 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 navigation1, at the same time it ensures safety and keeps training cost acceptable. } }
Endnote
%0 Conference Paper %T Intervention Aided Reinforcement Learning for Safe and Practical Policy Optimization in Navigation %A Fan Wang %A Bo Zhou %A Ke Chen %A Tingxiang Fan %A Xi Zhang %A Jiangyong Li %A Hao Tian %A Jia Pan %B Proceedings of The 2nd Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2018 %E Aude Billard %E Anca Dragan %E Jan Peters %E Jun Morimoto %F pmlr-v87-wang18a %I PMLR %J Proceedings of Machine Learning Research %P 410--421 %U http://proceedings.mlr.press %V 87 %W PMLR %X 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 pa- per, 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 navigation1, at the same time it ensures safety and keeps training cost acceptable.
APA
Wang, F., Zhou, B., Chen, K., Fan, T., Zhang, X., Li, J., Tian, H. & Pan, J.. (2018). Intervention Aided Reinforcement Learning for Safe and Practical Policy Optimization in Navigation. Proceedings of The 2nd Conference on Robot Learning, in PMLR 87:410-421

Related Material