Neural Q-learning

被引：0

作者：

Stephan ten Hagen

Ben Kröse

机构：

[1] University of Amsterdam,Faculty of Science

来源：

Neural Computing & Applications | 2003年 / 12卷

关键词：

Feed-forward network; Learning from real systems; Nonlinear systems; Optimal control Reinforcement learning;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

In this paper we introduce a novel neural reinforcement learning method. Unlike existing methods, our approach does not need a model of the system and can be trained directly using the measurements of the system. We achieve this by only using one function approximator and approximate the improved policy from this. An experiment using a mobile robot shows that it can be trained using a real system within reasonable time.

引用

页码：81 / 88

页数：7

共 50 条

[31] Periodic Q-Learning
Lee, Donghwan
He, Niao
[J]. LEARNING FOR DYNAMICS AND CONTROL, VOL 120, 2020, 120 : 582 - 598
[32] Fuzzy Q-learning
Glorennec, PY
Jouffe, L
[J]. PROCEEDINGS OF THE SIXTH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS I - III, 1997, : 659 - 662
[33] Q-learning and robotics
Touzet, CF
Santos, JM
[J]. SIMULATION IN INDUSTRY 2001, 2001, : 685 - 689
[34] Logistic Q-Learning
Bas-Serrano, Joan
Curi, Sebastian
Krause, Andreas
Neu, Gergely
[J]. 24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130
[35] Robust Q-Learning
Ertefaie, Ashkan
McKay, James R.
Oslin, David
Strawderman, Robert L.
[J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2021, 116 (533) : 368 - 381
[36] Q-learning based on neural network in learning action selection of mobile robot
Qiao, Junfei
Hou, Zhanjun
Ruan, Xiaogang
[J]. 2007 IEEE INTERNATIONAL CONFERENCE ON AUTOMATION AND LOGISTICS, VOLS 1-6, 2007, : 263 - 267
[37] Enhancing Nash Q-learning and Team Q-learning mechanisms by using bottlenecks
Ghazanfari, Behzad
Mozayani, Nasser
[J]. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2014, 26 (06) : 2771 - 2783
[38] Comparison of Deep Q-Learning, Q-Learning and SARSA Reinforced Learning for Robot Local Navigation
Anas, Hafiq
Ong, Wee Hong
Malik, Owais Ahmed
[J]. ROBOT INTELLIGENCE TECHNOLOGY AND APPLICATIONS 6, 2022, 429 : 443 - 454
[39] Learning to Play Pac-Xon with Q-Learning and Two Double Q-Learning Variants
Schilperoort, Jits
Mak, Ivar
Drugan, Madalina M.
Wiering, Marco A.
[J]. 2018 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI), 2018, : 1151 - 1158
[40] Neural Q-Learning Based on Residual Gradient for Nonlinear Control Systems
Si, Yanna
Pu, Jiexin
Zang, Shaofei
[J]. ICCAIS 2019: THE 8TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND INFORMATION SCIENCES, 2019,

← 1 2 3 4 5 →