Reward Shaping for Reinforcement Learning by Emotion Expressions

被引：0

作者：

Hwang, K. S. ^{[1
]}

Ling, J. L. ^{[2
]}

Chen, Yu-Ying ^{[3
]}

Wang, Wei-Han ^{[4
]}

机构：

[1] Natl Sun Yat Sen Univ, Dept Elect Engn, Kaohsiung, Taiwan

[2] Shih Hsin Univ, Dept Informat Management, Taipei 11678, Taiwan

[3] Natl Chung Cheng Univ, Dept Elect Engn, Chiayi 621, Taiwan

[4] Precis Machinery Res & Dev Ctr, Taipei, Taiwan

来源：

2014 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC) | 2014年

关键词：

emotion expression; fuzzy theory; intelligent robots; reinforcement learning; FUZZY-LOGIC SYSTEMS;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, a non-expert learning system was proposed to guide the robots learn their behaviors by humans' emotional expressions. The proposed system used interval fuzzy type-2 algorithm to recognize the human's facial expressions, which were captured by a web camera. Furthermore, emotion value (E-value), generated based on non-expert human's facial expressions, was applied to the reinforcement learning to train robots. Two kinds of problems were experimented. One was the human being know the exact solution to train robots and could clearly observe good or bad choice robots had been made. The other one was human being did not know the exact solution but robots could still learn from human's experience. The experiment results show that no matter the learning environment could be clearly observed by human being or not, robots could learn from human's facial expressions by the proposed learning system.

引用

页码：1288 / 1293

页数：6

共 50 条

[41] Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning
Hongyu Ding
Yuanze Tang
Qing Wu
Bo Wang
Chunlin Chen
Zhi Wang
[J]. IEEE/CAA Journal of Automatica Sinica, 2023, 10 (12) : 2233 - 2247
[42] On Reward Shaping Methods in Deep Reinforcement Learning for Radio Resource Management in Wireless Networks
Kopic, Amna
Turbic, Kenan
Gacanin, Haris
[J]. 2023 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS, ICC WORKSHOPS, 2023, : 1020 - 1025
[43] Hierarchical Reinforcement Learning from Demonstration via Reachability-Based Reward Shaping
Gao, Xiaozhu
Liu, Jinhui
Wan, Bo
An, Lingling
[J]. NEURAL PROCESSING LETTERS, 2024, 56 (03)
[44] Funnel-Based Reward Shaping for Signal Temporal Logic Tasks in Reinforcement Learning
Saxena, Naman
Gorantla, Sandeep
Jagtap, Pushpak
[J]. IEEE ROBOTICS AND AUTOMATION LETTERS, 2024, 9 (02): : 1373 - 1379
[45] Reinforcement Learning-based Adversarial Attacks on Object Detectors using Reward Shaping
Shi, Zhenbo
Yang, Wei
Xu, Zhenbo
Yu, Zhidong
Huang, Liusheng
[J]. PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 8424 - 8432
[46] Distributed Control using Reinforcement Learning with Temporal-Logic-Based Reward Shaping
Zhang, Ningyuan
Liu, Wenliang
Belta, Calin
[J]. LEARNING FOR DYNAMICS AND CONTROL CONFERENCE, VOL 168, 2022, 168
[47] Emotion-Based Heterogeneous Multi-agent Reinforcement Learning with Sparse Reward
Fang, Baofu
Ma, Yunting
Wang, Zaijun
Wang, Hao
[J]. Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2021, 34 (03): : 223 - 231
[48] Reward Reports for Reinforcement Learning
Gilbert, Thomas Krendl
Lambert, Nathan
Dean, Sarah
Zick, Tom
Snoswell, Aaron
Mehta, Soham
[J]. PROCEEDINGS OF THE 2023 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY, AIES 2023, 2023, : 84 - 130
[49] Reward, motivation, and reinforcement learning
Dayan, P
Balleine, BW
[J]. NEURON, 2002, 36 (02) : 285 - 298
[50] Deep reinforcement learning with reward shaping for tracking control and vibration suppression of flexible link manipulator
Viswanadhapalli, Joshi Kumar
Elumalai, Vinodh Kumar
Shivram, S.
Shah, Sweta
Mahajan, Dhruv
[J]. APPLIED SOFT COMPUTING, 2024, 152

← 1 2 3 4 5 →