author = "Santiago J{\'u}nior, Valdivino Alexandre de and {\"O}zcan, Ender 
                         and Carvalho, Vinicius Renan de",
          affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {University 
                         of Nottingham} and {Universidade de S{\~a}o Paulo (USP)}",
                title = "Hyper-Heuristics based on reinforcement learning, balanced 
                         heuristic selection and group decision acceptance",
              journal = "Applied Soft Computing Journal",
                 year = "2020",
               volume = "97",
                pages = "e106760",
                month = "Dec.",
             keywords = "Hyper-heuristic, Reinforcement learning, Balanced heuristic 
                         selection, Group decision-making, Multi-objective evolutionary 
                         algorithms, Multi-objective optimisation.",
             abstract = "In this paper, we introduce a multi-objective selection 
                         hyper-heuristic approach combining Reinforcement Learning, 
                         (meta)heuristic selection, and group decision-making as acceptance 
                         methods, referred to as Hyper-Heuristic based on Reinforcement 
                         LearnIng, Balanced Heuristic Selection and Group Decision 
                         AccEptance (HRISE), controlling a set of Multi-Objective 
                         Evolutionary Algorithms (MOEAs) as Low-Level (meta)Heuristics 
                         (LLHs). Along with the use of multiple MOEAs, we believe that 
                         having a robust LLH selection method as well as several move 
                         acceptance methods at our disposal would lead to an improved 
                         general-purpose method producing most adequate solutions to the 
                         problem instances across multiple domains. We present two learning 
                         hyper-heuristics based on the HRISE framework for multi-objective 
                         optimisation, each embedding a group decision-making acceptance 
                         method under a different rule: majority rule (HRISE_M) and 
                         responsibility rule (HRISE_R). A third hyper-heuristic is also 
                         defined where both a random LLH selection and a random move 
                         acceptance strategy are used. We also propose two variants of the 
                         late acceptance method and a new quality indicator supporting the 
                         initialisation of selection hyper-heuristics using low 
                         computational budget. An extensive set of experiments were 
                         performed using 39 multi-objective problem instances from various 
                         domains where 24 are from four different benchmark function 
                         classes, and the remaining 15 instances are from four different 
                         real-world problems. The cross-domain search performance of the 
                         proposed learning hyperheuristics indeed turned out to be the 
                         best, particularly HRISE_R, when compared to three other selection 
                         hyper-heuristics, including a recently proposed one, and all 
                         low-level MOEAs each run in isolation.",
                  doi = "10.1016/j.asoc.2020.106760",
                  url = "",
                 issn = "1568-4946 and 1872-9681",
             language = "en",
           targetfile = "valdivino_hyper.pdf",
        urlaccessdate = "2020, Nov. 26"