We discuss a coevolutionary genetic algorithm for constraint satisfaction. Our basic idea is to explore effective genetic information in the population, i.e., schemata, and to exploit the genetic information in order to guide the population to better solutions. Our coevolutionary genetic algorithm (CGA) consists of two GA populations; the first GA, called “H-GA”, searches for the solutions in a given environment (problem), and the second GA, called “P-GA”, searches for effective genetic information involved in the H-GA, namely, good schemata. Thus, each individual in P-GA consists of alleles in H-GA or “don't care” symbol representing a schema in the H-GA. These GA populations separately evolve in each genetic space at different abstraction levels and affect with each other by two genetic operators: “superposition” and “transcription”. We then applied our CGA to constraint satisfaction problems (CSPs) incorporating a new stochastic “repair” operator for P-GA to raise the consistency of schemata with the (local) constraint conditions in CSPs. We carried out two experiments: First, we examined the performance of CGA on various “general” CSPs that are generated randomly for a wide variety of “density” and “tightness” of constraint conditions in the CSPs that are the basic measures of characterizing CSPs. Next, we examined “structured” CSPs involving latent “cluster” structures among the variables in the CSPs. For these experiments, computer simulations confirmed us the effectiveness of our CGA
en-copyright= kn-copyright= en-aut-name=YamamotoHisashi en-aut-sei=Yamamoto en-aut-mei=Hisashi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=1 ORCID= en-aut-name=WatanabeKatsuyuki en-aut-sei=Watanabe en-aut-mei=Katsuyuki kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=2 ORCID= en-aut-name=KataiOsamu en-aut-sei=Katai en-aut-mei=Osamu kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=3 ORCID= en-aut-name=KonishiTadataka en-aut-sei=Konishi en-aut-mei=Tadataka kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=4 ORCID= en-aut-name=BabaMitsuru en-aut-sei=Baba en-aut-mei=Mitsuru kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=5 ORCID= affil-num=1 en-affil= kn-affil=Okayama University affil-num=2 en-affil= kn-affil=Kyoto University affil-num=3 en-affil= kn-affil=Kyoto University affil-num=4 en-affil= kn-affil=Okayama University affil-num=5 en-affil= kn-affil=Okayama University en-keyword=constraint theory kn-keyword=constraint theory en-keyword=genetic algorithms kn-keyword=genetic algorithms en-keyword=graph colouring kn-keyword=graph colouring END start-ver=1.4 cd-journal=joma no-vol=3 cd-vols= no-issue= article-no= start-page=1436 end-page=1441 dt-received= dt-revised= dt-accepted= dt-pub-year=2001 dt-pub=200110 dt-online= en-article= kn-article= en-subject= kn-subject= en-title= kn-title=Adaptive state construction for reinforcement learning and its application to robot navigation problems en-subtitle= kn-subtitle= en-abstract= kn-abstract=This paper applies our state construction method by ART neural network to robot navigation problems. Agents in this paper consist of ART neural network and contradiction resolution mechanism. The ART neural network serves as a mean of state recognition which maps stimulus inputs to a certain state and state construction which creates a new state when a current stimulus input cannot be categorized into any known states. On the other hand, the contradiction resolution mechanism (CRM) uses agents' state transition table to detect inconsistency among constructed states. In the proposed method, two kinds of inconsistency for the CRM are introduced: "Different results caused by the same states and the same actions" and "Contradiction due to ambiguous states." The simulation results on the robot navigation problems confirm the effectiveness of the proposed method
en-copyright= kn-copyright= en-aut-name=HandaHisashi en-aut-sei=Handa en-aut-mei=Hisashi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=1 ORCID= en-aut-name=NinomiyaAkira en-aut-sei=Ninomiya en-aut-mei=Akira kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=2 ORCID= en-aut-name=HoriuchiTadashi en-aut-sei=Horiuchi en-aut-mei=Tadashi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=3 ORCID= en-aut-name=KonishiTadataka en-aut-sei=Konishi en-aut-mei=Tadataka kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=4 ORCID= en-aut-name=BabaMitsuru en-aut-sei=Baba en-aut-mei=Mitsuru kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=5 ORCID= affil-num=1 en-affil= kn-affil=Okayama University affil-num=2 en-affil= kn-affil=Okayama University affil-num=3 en-affil= kn-affil=Matsue National College of Technology affil-num=4 en-affil= kn-affil=Chugoku Polytechnic College affil-num=5 en-affil= kn-affil=Okayama University en-keyword=Adaptive State Construction kn-keyword=Adaptive State Construction en-keyword=ART Neural Network kn-keyword=ART Neural Network en-keyword=Reinforcement Learning kn-keyword=Reinforcement Learning END