Modified reward function on abstract features in inverse reinforcement learning

Shen-yi CHEN; Hui QIAN; Jia FAN; Zhuo-jun JIN; Miao-liang ZHU

doi:10.1631/jzus.C0910486

Your Location：

Home >

Browse articles >

Modified reward function on abstract features in inverse reinforcement learning

计算机与自动化 | Updated：2022-08-31

- Modified reward function on abstract features in inverse reinforcement learning
- Modified reward function on abstract features in inverse reinforcement learning
- 信息与电子工程前沿（英文） 2010年11卷第9期页码：718-723
- Affiliations：
  
  School of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
- Author bio：
  
  E-mail:charles_csy@zju.edu.cn
- Funds：
- DOI：10.1631/jzus.C0910486
  中图分类号：
- 收稿：2009-08-07，
  
  修回：2010-05-31，
  
  录用：2009-10-19，
  
  纸质出版：2010-09
- Accepted：
Scan QR Code
Modified reward function on abstract features in inverse reinforcement learning[J]. 信息与电子工程前沿（英文）, 2010,11(9):718-723.

Shen-yi CHEN, Hui QIAN, Jia FAN, et al. Modified reward function on abstract features in inverse reinforcement learning[J]. Frontiers of Information Technology & Electronic Engineering, 2010, 11(9): 718-723.
Modified reward function on abstract features in inverse reinforcement learning[J]. 信息与电子工程前沿（英文）, 2010,11(9):718-723. DOI： 10.1631/jzus.C0910486.

Shen-yi CHEN, Hui QIAN, Jia FAN, et al. Modified reward function on abstract features in inverse reinforcement learning[J]. Frontiers of Information Technology & Electronic Engineering, 2010, 11(9): 718-723. DOI： 10.1631/jzus.C0910486.

摘要

Abstract

We improve inverse reinforcement learning (IRL) by applying dimension reduction methods to automatically extract abstract features from human-demonstrated policies

to deal with the cases where features are either unknown or numerous. The importance rating of each abstract feature is incorporated into the reward function. Simulation is performed on a task of driving in a five-lane highway

where the controlled car has the largest fixed speed among all the cars. Performance is almost 10.6% better on average with than without importance ratings.

关键词

Keywords

references

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Multiscale classification and its application to process monitoring