An online scalarization multi-objective reinforcement learning algorithm: TOPSIS Q-learning.
Mohammad MirzanejadMorteza EbrahimiPeter VamplewHadi VeisiPublished in: Knowl. Eng. Rev. (2022)
Keyphrases
- multi objective
- evolutionary algorithm
- multiple criteria
- optimization algorithm
- multi objective optimization
- multiobjective optimization
- multi criteria
- genetic algorithm
- multiple objectives
- particle swarm optimization
- online learning
- objective function
- state space
- nsga ii
- multi agent
- reinforcement learning
- function approximation
- pareto optimal
- differential evolution
- learning algorithm
- learning rate
- group decision making
- conflicting objectives
- optimum design
- real time
- mobile robot
- search space
- cooperative
- reinforcement learning algorithms
- bi objective
- multi objective evolutionary