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

[1] Belief Reward Shaping in Reinforcement Learning
Marom, Ofir
Rosman, Benjamin
[J]. THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 3762 - 3769
[2] Multigrid Reinforcement Learning with Reward Shaping
Grzes, Marek
Kudenko, Daniel
[J]. ARTIFICIAL NEURAL NETWORKS - ICANN 2008, PT I, 2008, 5163 : 357 - 366
[3] Reward Shaping in Episodic Reinforcement Learning
Grzes, Marek
[J]. AAMAS'17: PROCEEDINGS OF THE 16TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, 2017, : 565 - 573
[4] Hindsight Reward Shaping in Deep Reinforcement Learning
de Villiers, Byron
Sabatta, Deon
[J]. 2020 INTERNATIONAL SAUPEC/ROBMECH/PRASA CONFERENCE, 2020, : 653 - 659
[5] Reward Shaping Based Federated Reinforcement Learning
Hu, Yiqiu
Hua, Yun
Liu, Wenyan
Zhu, Jun
[J]. IEEE ACCESS, 2021, 9 : 67259 - 67267
[6] Reinforcement Learning with Reward Shaping and Hybrid Exploration in Sparse Reward Scenes
Yang, Yulong
Cao, Weihua
Guo, Linwei
Gan, Chao
Wu, Min
[J]. 2023 IEEE 6TH INTERNATIONAL CONFERENCE ON INDUSTRIAL CYBER-PHYSICAL SYSTEMS, ICPS, 2023,
[7] Using Natural Language for Reward Shaping in Reinforcement Learning
Goyal, Prasoon
Niekum, Scott
Mooney, Raymond J.
[J]. PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 2385 - 2391
[8] Plan-based Reward Shaping for Reinforcement Learning
Grzes, Marek
Kudenko, Daniel
[J]. 2008 4TH INTERNATIONAL IEEE CONFERENCE INTELLIGENT SYSTEMS, VOLS 1 AND 2, 2008, : 416 - 423
[9] Theoretical and Empirical Analysis of Reward Shaping in Reinforcement Learning
Grzes, Marek
Kudenko, Daniel
[J]. EIGHTH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, PROCEEDINGS, 2009, : 337 - 344
[10] Reinforcement online learning to rank with unbiased reward shaping
Zhuang, Shengyao
Qiao, Zhihao
Zuccon, Guido
[J]. INFORMATION RETRIEVAL JOURNAL, 2022, 25 (04): : 386 - 413

← 1 2 3 4 5 →