Print Email Facebook Twitter Efficient Online Globalized Dual Heuristic Programming With an Associated Dual Network Title Efficient Online Globalized Dual Heuristic Programming With an Associated Dual Network Author Zhou, Y. (TU Delft Control & Simulation; Universiti Sains Malaysia) Date 2022 Abstract Globalized dual heuristic programming (GDHP) is the most comprehensive adaptive critic design, which employs its critic to minimize the error with respect to both the cost-to-go and its derivatives simultaneously. Its implementation, however, confronts a dilemma of either introducing more computational load by explicitly calculating the second partial derivative term or sacrificing the accuracy by loosening the association between the cost-to-go and its derivatives. This article aims at increasing the online learning efficiency of GDHP while retaining its analytical accuracy by introducing a novel GDHP design based on a critic network and an associated dual network. This associated dual network is derived from the critic network explicitly and precisely, and its structure is in the same level of complexity as dual heuristic programming critics. Three simulation experiments are conducted to validate the learning ability, efficiency, and feasibility of the proposed GDHP critic design. Subject Adaptation modelsAdaptive critic designs (ACDs)BackpropagationComplexity theoryCostsglobalized dual heuristic programmingincremental modelMathematical modelsneural networksProgrammingradial basis functionsreinforcement learning (RL).Task analysis To reference this document use: http://resolver.tudelft.nl/uuid:319f01fe-2dfe-4507-89bc-071a629b8db4 DOI https://doi.org/10.1109/TNNLS.2022.3164727 Embargo date 2023-12-19 ISSN 2162-237X Source IEEE Transactions on Neural Networks and Learning Systems, 34 (12), 10079-10090 Part of collection Institutional Repository Document type journal article Rights © 2022 Y. Zhou Files PDF Efficient_Online_Globaliz ... etwork.pdf 1.89 MB Close viewer /islandora/object/uuid:319f01fe-2dfe-4507-89bc-071a629b8db4/datastream/OBJ/view