Attention-Based Deep Q-Network in Complex Systems

The present chapter of this book delves into the exploration of metaheuristic algorithms as an avenue for solving optimization problems pertaining to engineering and intricate systems. Metaheuristics which encompass a diverse array of intelligent search and optimization techniques inspired by natural phenomena, have demonstrated their efficacy in addressing intricate, nonlinear, and multi-objective optimization challenges. Furthermore, a thorough and comprehensive overview of metaheuristic algorithms, including genetic algorithms, simulated annealing, particle swarm optimization, and ant colony optimization, among others, is provided. Additionally, the chapter delves into the synergistic potential of combining metaheuristics with other optimization techniques, as well as machine learning and data-driven approaches. Ultimately, this chapter culminates in serving as a valuable resource for researchers, practitioners, and students who possess an interest in employing metaheuristics for the optimization of engineering and complex systems.

show abstract

Attention-Based Deep Q-Network in Complex Systems

Cited by 3 publications

References 3 publications

Comparative DQN-Improved Algorithms for Stochastic Games-Based Automated Edge Intelligence-Enabled IoT Malware Spread-Suppression Strategies

Comparative DQN-Improved Algorithms for Stochastic Games-Based Automated Edge Intelligence-Enabled IoT Malware Spread-Suppression Strategies

Cascaded Attention: Adaptive and Gated Graph Attention Network for Multiagent Reinforcement Learning

Meta-Heuristic and Machine Learning Modelling and Optimizing Complex Systems

Contact Info

Product

Resources

About