Deep reinforcement learning-based framework for constrained any-objective optimization
H Honari, S Khodaygan - Journal of Ambient Intelligence and Humanized …, 2023 - Springer
Optimization problems are widely used in many real-world applications. These problems are
rarely unconstrained and are usually considered constrained optimization problems …
rarely unconstrained and are usually considered constrained optimization problems …
Multiobjective optimization algorithm with objective-wise learning for continuous multiobjective problems
J Wang, C Zhong, Y Zhou, Y Zhou - Journal of Ambient Intelligence and …, 2015 - Springer
Most of multiobjective optimization algorithms consider multiple objectives as a whole when
solving multiobjective optimization problems (MOPs). However, in MOPs, different objective …
solving multiobjective optimization problems (MOPs). However, in MOPs, different objective …
Multi-Objective and Constrained Reinforcement Learning for IoT
S Vaishnav, S Magnússon - Learning Techniques for the Internet of Things, 2023 - Springer
IoT networks of the future will be characterized by autonomous decision-making by
individual devices. Decision-making is done with the purpose of optimizing certain …
individual devices. Decision-making is done with the purpose of optimizing certain …
Efficient elitist cooperative evolutionary algorithm for multi-objective reinforcement learning
D Zhou, J Du, S Arai - IEEE Access, 2023 - ieeexplore.ieee.org
Sequential decision-making problems with multiple objectives are known as multi-objective
reinforcement learning. In these scenarios, decision-makers require a complete Pareto front …
reinforcement learning. In these scenarios, decision-makers require a complete Pareto front …
MODRL/D-AM: Multiobjective deep reinforcement learning algorithm using decomposition and attention model for multiobjective optimization
H Wu, J Wang, Z Zhang - … , ISICA 2019, Guangzhou, China, November 16 …, 2020 - Springer
Recently, a deep reinforcement learning method is proposed to solve multiobjective
optimization problem. In this method, the multiobjective optimization problem is decomposed …
optimization problem. In this method, the multiobjective optimization problem is decomposed …
Deep reinforcement learning for multiobjective optimization
This article proposes an end-to-end framework for solving multiobjective optimization
problems (MOPs) using deep reinforcement learning (DRL), that we call DRL-based …
problems (MOPs) using deep reinforcement learning (DRL), that we call DRL-based …
Constrained multi-objective optimization with deep reinforcement learning assisted operator selection
Solving constrained multi-objective optimization problems with evolutionary algorithms has
attracted considerable attention. Various constrained multi-objective optimization …
attracted considerable attention. Various constrained multi-objective optimization …
An information entropy-driven evolutionary algorithm based on reinforcement learning for many-objective optimization
Many-objective optimization problems (MaOPs) are challenging tasks involving optimizing
many conflicting objectives simultaneously. Decomposition-based many-objective …
many conflicting objectives simultaneously. Decomposition-based many-objective …
Meta-learning-based deep reinforcement learning for multiobjective optimization problems
Z Zhang, Z Wu, H Zhang, J Wang - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Deep reinforcement learning (DRL) has recently shown its success in tackling complex
combinatorial optimization problems. When these problems are extended to multiobjective …
combinatorial optimization problems. When these problems are extended to multiobjective …
Multi-objective pointer network for combinatorial optimization
Multi-objective combinatorial optimization problems (MOCOPs), one type of complex
optimization problems, widely exist in various real applications. Although meta-heuristics …
optimization problems, widely exist in various real applications. Although meta-heuristics …