Modified reward function on abstract features in inverse reinforcement learning

被引：2

作者：

Shenyi CHENHui QIANJia FANZhuojun JINMiaoliang ZHUSchool of Computer Science and TechnologyZhejiang UniversityHangzhou China ^{[310027
]}

机构：

来源：

Journal of Zhejiang University-Science C(Computer & Electronics) | 2010年 / 11卷 / 09期

关键词：

D O I：

暂无

中图分类号：

TP181 [自动推理、机器学习];

学科分类号：

摘要：

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.

引用

页码：718 / 723

页数：6

共 50 条

[21] Reinforcement Learning with Converging Goal Space and Binary Reward Function
Ro, Wooseok
Jeon, Wonseok
Bamshad, Hamid
Yang, Hyunseok
2020 IEEE 16TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE), 2020, : 921 - 927
[22] Reward Function Evaluation in a Reinforcement Learning Approach for Energy Management
Rioual, Yohann
Le Moullec, Yannick
Laurent, Johann
Khan, Muhidul Islam
Diguet, Jean-Philippe
2018 16TH BIENNIAL BALTIC ELECTRONICS CONFERENCE (BEC), 2018,
[23] On Reward-Free Reinforcement Learning with Linear Function Approximation
Wang, Ruosong
Du, Simon S.
Yang, Lin F.
Salakhutdinov, Ruslan
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
[24] A Hierarchical Reinforcement Learning Algorithm Based On Heuristic Reward Function
Yan, Qicui
Liu, Quan
Hu, Daojing
2ND IEEE INTERNATIONAL CONFERENCE ON ADVANCED COMPUTER CONTROL (ICACC 2010), VOL. 3, 2010, : 371 - 376
[25] Reward Function Design for Crowd Simulation via Reinforcement Learning
Kwiatkowski, Ariel
Kalogeiton, Vicky
Pettre, Julien
Cani, Marie-Paule
15TH ANNUAL ACM SIGGRAPH CONFERENCE ON MOTION, INTERACTION AND GAMES, MIG 2023, 2023,
[26] Robust Adaptive Scaffolding with Inverse Reinforcement Learning-Based Reward Design
Fahid, Fahmid Morshed
Rowe, Jonathan P.
Spain, Randall D.
Goldberg, Benjamin S.
Pokorny, Robert
Lester, James
ARTIFICIAL INTELLIGENCE IN EDUCATION: POSTERS AND LATE BREAKING RESULTS, WORKSHOPS AND TUTORIALS, INDUSTRY AND INNOVATION TRACKS, PRACTITIONERS AND DOCTORAL CONSORTIUM, PT II, 2022, 13356 : 204 - 207
[27] Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning
Ghosh, Sayan
Srivastava, Shashank
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2021, 2021, : 1449 - 1462
[28] Improved Reward Estimation for Efficient Robot Navigation Using Inverse Reinforcement Learning
Saha, Olimpiya
Dasgupta, Prithviraj
2017 NASA/ESA CONFERENCE ON ADAPTIVE HARDWARE AND SYSTEMS (AHS), 2017, : 245 - 252
[29] Nonparametric Bayesian Reward Segmentation for Skill Discovery Using Inverse Reinforcement Learning
Ranchod, Pravesh
Rosman, Benjamin
Konidaris, George
2015 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2015, : 471 - 477
[30] State-space Model Based Inverse Reinforcement Learning for Reward Function Estimation in Brain-machine Interfaces
Tan, Jieyuan
Zhang, Xiang
Wu, Shenghui
Wang, Yiwen
2023 45TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY, EMBC, 2023,

← 1 2 3 4 5 →