Automatic generation of macro-actions using genetic algorithm for reinforcement learning

被引：0

作者：

Tateyama, T ^{[1
]}

Kawata, S ^{[1
]}

Oguchi, T ^{[1
]}

机构：

[1] Tokyo Metropolitan Univ, Grad Sch Engn, Hachioji, Tokyo 1920397, Japan

来源：

SICE 2002: PROCEEDINGS OF THE 41ST SICE ANNUAL CONFERENCE, VOLS 1-5 | 2002年

关键词：

reinforcement learning; macro-action; Semi-Markov Decision Processes; classifier system;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The main problem of reinforcement learning is that learning converges slowly. As one of the solution, McGovern proposed "macro-action". However, a human expert needs to design macro-actions which adapt to an environment. In this paper, we propose a new method that enables to generate the macro-actions which adapt to the enviroment automatically using genetic algorithm.

引用

页码：286 / 289

页数：4

共 50 条

[41] Using a Genetic Algorithm to Improve Recurrent Reinforcement Learning for Equity Trading
Jin Zhang
Dietmar Maringer
[J]. Computational Economics, 2016, 47 : 551 - 567
[42] Automatic Game World Generation for Platformer Games Using Genetic Algorithm
Kholimi, Ali Sofyan
Hamdani, Ahmad
Husniah, Lailatul
[J]. 2018 5TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING, COMPUTER SCIENCE AND INFORMATICS (EECSI 2018), 2018, : 495 - 498
[43] Using a Genetic Algorithm to Improve Recurrent Reinforcement Learning for Equity Trading
Zhang, Jin
Maringer, Dietmar
[J]. COMPUTATIONAL ECONOMICS, 2016, 47 (04) : 551 - 567
[44] A Parallel Hybrid Implementation Using Genetic Algorithm, GRASP and Reinforcement Learning
Queiroz dos Santos, Joao Paulo
de Lima Junior, Francisco Chagas
Magalhaes, Rafael Marrocos
de Melo, Jorge Dantas
Doria Neto, Adriao Duarte
[J]. IJCNN: 2009 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1- 6, 2009, : 2502 - +
[45] Automatic structural test data generation using immune genetic algorithm
Yong, Chen
Yong, Zhong
Bao Sheng-Li
He Fa-Mei
[J]. PROCEEDINGS OF THE INTERNATIONAL CONFERENCE INFORMATION COMPUTING AND AUTOMATION, VOLS 1-3, 2008, : 688 - 690
[46] Deep Reinforcement Learning for Decentralized Multi-Robot Exploration With Macro Actions
Tan, Aaron Hao
Bejarano, Federico Pizarro
Zhu, Yuhan
Ren, Richard
Nejat, Goldie
[J]. IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (01) : 272 - 279
[47] NeuroCrossover: An intelligent genetic locus selection scheme for genetic algorithm using reinforcement learning
Liu, Haoqiang
Zong, Zefang
Li, Yong
Jin, Depeng
[J]. APPLIED SOFT COMPUTING, 2023, 146
[48] PORTAL: Automatic Curricula Generation for Multiagent Reinforcement Learning
Wu, Jizhou
Hao, Jianye
Yang, Tianpei
Hao, Xiaotian
Zheng, Yan
Wang, Weixun
Taylor, Matthew E.
[J]. THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 14, 2024, : 15934 - 15942
[49] Automatic Curriculum Graph Generation for Reinforcement Learning Agents
Svetlik, Maxwell
Leonetti, Matteo
Sinapov, Jivko
Shah, Rishi
Walker, Nick
Stone, Peter
[J]. THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 2590 - 2596
[50] Learning algorithm by reinforcement signals for the automatic recognition system
Ikuta, K
Tanaka, KI
Tanaka, H
Kyuma, K
[J]. 2004 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN & CYBERNETICS, VOLS 1-7, 2004, : 4844 - 4848

← 1 2 3 4 5 →