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
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
收藏
页码:1349 / 1350
页数:2
相关论文
共 50 条
  • [31] Multi-objective multicast optimization with deep reinforcement learning
    Li, Xiaole
    Tian, Jinwei
    Wang, Cuiping
    Jiang, Yinghui
    Wang, Xing
    Wang, Jiuru
    CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2025, 28 (04):
  • [32] Dynamic Weights in Multi-Objective Deep Reinforcement Learning
    Abels, Axel
    Roijers, Diederik M.
    Lenaerts, Tom
    Nowe, Ann
    Steckelmacher, Denis
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
  • [33] Model-Based Multi-Objective Reinforcement Learning
    Wiering, Marco A.
    Withagen, Maikel
    Drugan, Madalina M.
    2014 IEEE SYMPOSIUM ON ADAPTIVE DYNAMIC PROGRAMMING AND REINFORCEMENT LEARNING (ADPRL), 2014, : 111 - 116
  • [34] Taming Lagrangian chaos with multi-objective reinforcement learning
    Chiara Calascibetta
    Luca Biferale
    Francesco Borra
    Antonio Celani
    Massimo Cencini
    The European Physical Journal E, 2023, 46
  • [35] Track Learning Agent Using Multi-objective Reinforcement Learning
    Shah, Rushabh
    Ruparel, Vidhi
    Prabhu, Mukul
    D'mello, Lynette
    FOURTH CONGRESS ON INTELLIGENT SYSTEMS, VOL 1, CIS 2023, 2024, 868 : 27 - 40
  • [36] Evolutionary Reinforcement Learning for Multi-objective SFC Deployment
    Zhao, Jialiang
    Wang, Ran
    Wu, Qiang
    Hao, Jie
    Xiong, Zehui
    2024 IEEE 21ST INTERNATIONAL CONFERENCE ON MOBILE AD-HOC AND SMART SYSTEMS, MASS 2024, 2024, : 212 - 218
  • [37] A reinforcement learning approach for dynamic multi-objective optimization
    Zou, Fei
    Yen, Gary G.
    Tang, Lixin
    Wang, Chunfeng
    INFORMATION SCIENCES, 2021, 546 : 815 - 834
  • [38] A practical guide to multi-objective reinforcement learning and planning
    Hayes, Conor F.
    Radulescu, Roxana
    Bargiacchi, Eugenio
    Kallstrom, Johan
    Macfarlane, Matthew
    Reymond, Mathieu
    Verstraeten, Timothy
    Zintgraf, Luisa M.
    Dazeley, Richard
    Heintz, Fredrik
    Howley, Enda
    Irissappane, Athirai A.
    Mannion, Patrick
    Nowe, Ann
    Ramos, Gabriel
    Restelli, Marcello
    Vamplew, Peter
    Roijers, Diederik M.
    AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS, 2022, 36 (01)
  • [39] Multi-objective Genetic Programming for Explainable Reinforcement Learning
    Videau, Mathurin
    Leite, Alessandro
    Teytaud, Olivier
    Schoenauer, Marc
    GENETIC PROGRAMMING (EUROGP 2022), 2022, : 278 - 293
  • [40] Multi-Objective Optimization in Disaster Backup with Reinforcement Learning
    Yi, Shanwen
    Qin, Yao
    Wang, Hua
    MATHEMATICS, 2025, 13 (03)