PMDRL: Pareto-front-based multi-objective deep reinforcement learning.
Fangjie YangHonglan HuangWei ShiYang MaYanghe FengGuangquan ChengZhong LiuPublished in: J. Ambient Intell. Humaniz. Comput. (2023)
Keyphrases
- multi objective
- reinforcement learning
- multi objective optimization
- evolutionary algorithm
- optimization algorithm
- multiobjective optimization
- objective function
- particle swarm optimization
- nsga ii
- multiple objectives
- genetic algorithm
- function approximation
- reinforcement learning algorithms
- pareto optimal
- multi objective optimization problems
- evolutionary optimization
- pareto optimal solutions
- state space
- markov decision processes
- pareto fronts
- multi agent
- engineering design problems
- conflicting objectives
- model free
- optimal policy
- multi objective evolutionary
- multi objective evolutionary algorithms
- multi criteria
- learning algorithm
- bi objective
- action selection
- optimal control
- learning process
- machine learning
- learning classifier systems
- robotic control