Adaptive Objective Selection for Correlated Objectives in Multi-Objective Reinforcement Learning

被引：0

作者：

Brys, Tim ^{[1
]}

Van Moffaert, Kristof ^{[1
]}

Nowe, Ann ^{[1
]}

Taylor, Matthew E. ^{[2
]}

机构：

[1] Vrije Univ Brussel, Brussels, Belgium

[2] Washington State Univ, Pullman, WA 99164 USA

来源：

AAMAS'14: PROCEEDINGS OF THE 2014 INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS & MULTIAGENT SYSTEMS | 2014年

关键词：

Reinforcement Learning; Multi-Objective Optimization; Adaptive Objective Selection;

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：

In this paper we introduce a novel scale-invariant and parameterless technique, called adaptive objective selection, that allows a temporal-difference learning agent to exploit the correlation between objectives in a multi-objective problem. It identifies and follows in each state the objective whose estimates it is most confident about. We propose several variants of the approach and empirically demonstrate it on a toy problem.

引用

页码：1349 / 1350

页数：2

共 50 条

[21] Constrained Multi-Objective Optimization With Deep Reinforcement Learning Assisted Operator Selection
Ming, Fei
Gong, Wenyin
Wang, Ling
Jin, Yaochu
IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2024, 11 (04) : 919 - 931
[22] Constrained Multi-Objective Optimization With Deep Reinforcement Learning Assisted Operator Selection
Fei Ming
Wenyin Gong
Ling Wang
Yaochu Jin
IEEE/CAAJournalofAutomaticaSinica, 2024, 11 (04) : 919 - 959
[23] A Multi-objective Reinforcement Learning Algorithm for JS']JSSP
Mendez-Hernandez, Beatriz M.
Rodriguez-Bazan, Erick D.
Martinez-Jimenez, Yailen
Libin, Pieter
Nowe, Ann
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: THEORETICAL NEURAL COMPUTATION, PT I, 2019, 11727 : 567 - 584
[24] Multi-Objective Service Composition Using Reinforcement Learning
Moustafa, Ahmed
Zhang, Minjie
SERVICE-ORIENTED COMPUTING, ICSOC 2013, 2013, 8274 : 298 - 312
[25] Taming Lagrangian chaos with multi-objective reinforcement learning
Calascibetta, Chiara
Biferale, Luca
Borra, Francesco
Celani, Antonio
Cencini, Massimo
EUROPEAN PHYSICAL JOURNAL E, 2023, 46 (03):
[26] Multi-Objective Reinforcement Learning for Designing Ethical Environments
Rodriguez-Soto, Manel
Lopez-Sanchez, Maite
Rodriguez-Aguilar, Juan A.
PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 545 - 551
[27] Urban Driving with Multi-Objective Deep Reinforcement Learning
Li, Changjian
Czarnecki, Krzysztof
AAMAS '19: PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, 2019, : 359 - 367
[28] A temporal difference method for multi-objective reinforcement learning
Ruiz-Montiel, Manuela
Mandow, Lawrence
Perez-de-la-Cruz, Jose-Luis
NEUROCOMPUTING, 2017, 263 : 15 - 25
[29] Multi-objective reinforcement learning approach for trip recommendation
Chen, Lei
Zhu, Guixiang
Liang, Weichao
Wang, Youquan
EXPERT SYSTEMS WITH APPLICATIONS, 2023, 226
[30] Multi-Objective Order Scheduling via Reinforcement Learning
Chen, Sirui
Tian, Yuming
An, Lingling
ALGORITHMS, 2023, 16 (11)

← 1 2 3 4 5 →