The IEEE Transactions on Neural Networks and Learning Systems publishes technical articles that deal with the theory, design, and applications of neural networks and related learning systems.
Journal Citation Metrics Journal Citation Metrics such as Impact Factor, Eigenfactor Score™ and Article Influence Score™ are available where applicable. Each year, Journal Citation Reports© (JCR) from Thomson Reuters examines the influence and impact of scholarly research journals. JCR reveals the relationship between citing and cited journals, offering a systematic, objective means to evaluate the world's leading journals. Find out more about IEEE Journal Bibliometrics.
Call for Special Issues
IEEE TNNLS Special Issue on "Deep Learning: When and How?" Guest Editors:Bart Baesens, KU Leuven, Belgium, María Óskarsdóttir, Reykjavik University, Iceland, Davide Bacciu, Universita' di Pisa, Italy, Hugo Jair Escalante, INAOE, Mexico, Rohitash Chandra, UNSW, Australia. Submission Deadline: April 23, 2023 [Call for Papers]
IEEE TNNLS Special Issue on "Graphic Learning" Guest Editors: Feng Xia, Federation University Australia, Australia, Renaud Lambiotte, University of Oxford, United Kingdom, Neil Shah, Snap Research, USA, Hanghang Tong, University of Illinois Urbana-Champaign, USA, Irwin King, The Chinese University of Hong Kong, Hong Kong. Submission Deadline: March 1, 2023 [Call for Papers]
IEEE TNNLS Special Issue on "Learning Theories and Methods with Application to Digitized Process Manufacturing" Guest Editors: Feng Qian, East China University of Science and Technology, China, Yaochu Jin, Bielefeld University, Germany, Xinghuo Yu, Royal Melbourne Institute of Technology University, Australia, Yang Tang, East China University of Science and Technology, China, Guy B. Marin, Ghent University, Belgium. Submission Deadline: March 31, 2023 [Call for Papers]
IEEE TNNLS Special Issue on "Deep Learning for Intelligent Media Computing and Applications" Guest Editors: Hamido Fujita, Iwate Prefectural University, Japan, Bo Li, Northwestern Polytechnical University, China, Yiyu Yao, University of Regina, Canada, Xinbo Gao, Chongqing University of Posts and Telecommunications, China, Maoguo Gong, Xidian University, China, Ivan Lee, University of South Australia, Australia, Martin Ester, Simon Fraser University, Canada, Xin Wang, Tsinghua University, China. Submission Deadline: January 31, 2023 [Call for Papers]
IEEE TNNLS Special Issue on "Information Theoretic Methods for the Generalization, Robustness and Interpretability of Machine Learning" Guest Editors: Badong Chen, Xi’an Jiaotong University, China, Shujian Yu, UiT – The Arctic University of Norway, Norway, Robert Jenssen, UiT – The Arctic University of Norway, Norway, Jose C. Principe, University of Florida, USA, Klaus-Robert Müller, Technische Universität Berlin (TU Berlin), Germany. Submission Deadline: October 1, 2022 [Call for Papers]
The Boundedness Conditions for Model-Free HDP( λ )
Authors: Seaar Al-Dabooni, Donald Wunsch
Publication: IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
Issue: Volume 30, Issue 7 – July 2019
Abstract: This paper provides the stability analysis for a model-free action-dependent heuristic dynamic programing (HDP) approach with an eligibility trace long-term prediction parameter (λ). HDP(λ) learns from more than one future reward. Eligibility traces have long been popular in Q-learning. This paper proves and demonstrates that they are worthwhile to use with HDP. In this paper, we prove its uniformly ultimately bounded (UUB) property under certain conditions. Previous works present a UUB proof for traditional HDP [HDP(λ = 0)], but we extend the proof with the λ parameter. By using Lyapunov stability, we demonstrate the boundedness of the estimated error for the critic and actor neural networks as well as learning rate parameters. Three case studies demonstrate the effectiveness of HDP(λ). The trajectories of the internal reinforcement signal nonlinear system are considered as the first case. We compare the results with the performance of HDP and traditional temporal difference [TD(λ)] with different λ values. The second case study is a single-link inverted pendulum. We investigate the performance of the inverted pendulum by comparing HDP(λ) with regular HDP, with different levels of noise. The third case study is a 3-D maze navigation benchmark, which is compared with state action reward state action, Q(λ), HDP, and HDP(λ). All these simulation results illustrate that HDP(λ) has a competitive performance; thus this contribution is not only UUB but also useful in comparison with traditional HDP.
Index Terms: λ-return, action dependent (AD), approximate dynamic programing (ADP), heuristic dynamic programing (HDP), Lyapunov stability, model free, uniformly ultimately bounded (UUB)
IEEE Xplore Link: https://ieeexplore.ieee.org/document/8528554