Back to Search Start Over

NEARL: Non-Explicit Action Reinforcement Learning for Robotic Control

Authors :
Lin, Nan
Li, Yuxuan
Zhu, Yujun
Wang, Ruolin
Zhang, Xiayu
Ji, Jianmin
Tang, Keke
Chen, Xiaoping
Zhang, Xinming
Publication Year :
2020

Abstract

Traditionally, reinforcement learning methods predict the next action based on the current state. However, in many situations, directly applying actions to control systems or robots is dangerous and may lead to unexpected behaviors because action is rather low-level. In this paper, we propose a novel hierarchical reinforcement learning framework without explicit action. Our meta policy tries to manipulate the next optimal state and actual action is produced by the inverse dynamics model. To stabilize the training process, we integrate adversarial learning and information bottleneck into our framework. Under our framework, widely available state-only demonstrations can be exploited effectively for imitation learning. Also, prior knowledge and constraints can be applied to meta policy. We test our algorithm in simulation tasks and its combination with imitation learning. The experimental results show the reliability and robustness of our algorithms.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2011.01046
Document Type :
Working Paper