Reinforcement learning for enhanced online gradient-based parameter adaptation in metaheuristics.
Vasileios A. TatsisKonstantinos E. ParsopoulosPublished in: Swarm Evol. Comput. (2023)
Keyphrases
- reinforcement learning
- online learning
- function approximation
- particle swarm optimization
- real time
- machine learning
- learning algorithm
- optimization problems
- tabu search
- markov decision processes
- metaheuristic
- solution space
- state space
- combinatorial optimization
- parameter space
- optimal solution
- temporal difference learning
- adaptation process
- robotic control