SIMULTANEOUS FEATURE SELECTION AND PARAMETER OPTIMIZATION FOR TRAINING OF DIALOG POLICY BY REINFORCEMENT LEARNING

被引:0
作者
Misu, Teruhisa [1 ]
Kashioka, Hideki [1 ]
机构
[1] Natl Inst Informat & Commun Technol NICT, Kyoto, Japan
来源
2012 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2012) | 2012年
关键词
Spoken dialog systems; Dialog management; Reinforcement learning; Feature selection;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This paper addresses the problem of feature selection in the reinforcement learning (RL) of the dialog policies of spoken dialog systems. A statistical dialog manager selects the system actions the system should take based on the features derived from the current dialog state and/or the system's belief state. When defining the features used by the system for training the dialog policy, however, finding a set of actually effective features from potentially useful ones is not obvious. In addition, the selection should be done simultaneously with the optimization of the dialog policy. In this paper, we propose an incremental feature selection method for the optimization of a dialog policy by RL, in which improvement of the dialog policy and the feature selection are conducted simultaneously. Experiments in dialog policy optimization by RL with a user simulator demonstrated the following: 1) that the proposed method can find a better dialog policy with fewer policy iterations and 2) the learning speed is comparable with the case where feature selection is conducted in advance.
引用
收藏
页码:1 / 6
页数:6
相关论文
共 50 条
[31]   Causal Based Action Selection Policy for Reinforcement Learning [J].
Feliciano-Avelino, Ivan ;
Mendez-Molina, Arquimides ;
Morales, Eduardo F. ;
Enrique Sucar, L. .
ADVANCES IN COMPUTATIONAL INTELLIGENCE (MICAI 2021), PT I, 2021, 13067 :213-227
[32]   A simulated-annealing-based approach for simultaneous parameter optimization and feature selection of back-propagation networks [J].
Lin, Shih-Wei ;
Tseng, Tsung-Yuan ;
Chou, Shuo-Yan ;
Chen, Shih-Chieh .
EXPERT SYSTEMS WITH APPLICATIONS, 2008, 34 (02) :1491-1499
[33]   Network traffic classification using feature selection and parameter optimization [J].
Cao, Jie ;
Fang, Zhiyi ;
Zhang, Dan ;
Qu, Guannan .
Journal of Communications, 2015, 10 (10) :828-835
[34]   Crow Search Algorithm Boosted by Reinforcement Learning for Feature Selection [J].
Olivares, Rodrigo ;
Olivares, Pablo ;
Rios, Victor ;
Oliveros, Alejandro .
MACHINE LEARNING METHODS IN SYSTEMS, VOL 4, CSOC 2024, 2024, 1126 :144-151
[35]   Simultaneous feature selection and clustering based on square root optimization [J].
Jiang, He ;
Luo, Shihua ;
Dong, Yao .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2021, 289 (01) :214-231
[36]   Simultaneous Feature Selection and Clustering Using Particle Swarm Optimization [J].
Swetha, K. P. ;
Devi, V. Susheela .
NEURAL INFORMATION PROCESSING, ICONIP 2012, PT I, 2012, 7663 :509-515
[37]   Optimal feature selection through reinforcement learning and fuzzy signature for improving classification accuracy [J].
Mansouri N. ;
Zandvakili A. ;
Javidi M.M. .
Multimedia Tools and Applications, 2025, 84 (10) :6931-6965
[38]   A reinforcement learning approach for process parameter optimization in additive manufacturing [J].
Dharmadhikari, Susheel ;
Menon, Nandana ;
Basak, Amrita .
ADDITIVE MANUFACTURING, 2023, 71
[39]   Simultaneous Process Design and Control Optimization using Reinforcement Learning [J].
Sachio, Steven ;
Chanona, Antonio E. del-Rio ;
Petsagkourakis, Panagiotis .
IFAC PAPERSONLINE, 2021, 54 (03) :510-515
[40]   Quantum Optimization Approach for Feature Selection in Machine Learning [J].
Fleury, Gerard ;
Vulpescu, Bogdan ;
Lacomme, Philippe .
METAHEURISTICS, MIC 2024, PT I, 2024, 14753 :281-288