Multi-objective fuzzy Q-learning to solve continuous state-action problems
Authors:
- Amirhossein AsgharniaAAAmirhossein Asgharnia
- Howard SchwartzHSHoward Schwartz
- Mohamed AtiaMAMohamed Atia
- 21 October 2022
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 516, 115-132
Abstract
No abstract availableKeywords
Funding Information
- Natural Sciences and Engineering Research Council of Canada (RGPIN-2017–06261, RGPIN-2017–06379)
This publication has 26 references indexed in Scilit:
- Multiobjective Reinforcement Learning: A Comprehensive OverviewIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2014
- Hypervolume-Based Multi-Objective Reinforcement Learning2013
- Empirical evaluation methods for multiobjective reinforcement learning algorithmsMachine Learning, 2010
- Pareto optimization of a five-degree of freedom vehicle vibration model using a multi-objective uniform-diversity genetic algorithm (MUGA)Engineering Applications of Artificial Intelligence, 2010
- On the Limitations of Scalarisation for Multi-objective Reinforcement Learning of Pareto Fronts2008
- Performance assessment of multiobjective optimizers: an analysis and reviewIEEE Transactions on Evolutionary Computation, 2003
- A fast and elitist multiobjective genetic algorithm: NSGA-IIIEEE Transactions on Evolutionary Computation, 2002
- Q-learningMachine Learning, 1992
- The set of efficient solutions for multiple objective shortest path problemsComputers & Operations Research, 1982
- Note on Multiple Objective Dynamic ProgrammingJournal of the Operational Research Society, 1980