Multi-objective optimisation by reinforcement learning.
Huilian LiaoQ. H. WuPublished in: IEEE Congress on Evolutionary Computation (2010)
Keyphrases
- multi objective optimisation
- reinforcement learning
- multi objective
- multi objective optimization
- model free
- function approximation
- nsga ii
- state space
- temporal difference
- multiple objectives
- dynamic programming
- optimal policy
- reinforcement learning algorithms
- machine learning
- markov decision processes
- multiobjective optimization
- evolutionary algorithm
- multi agent
- robotic control
- learning problems
- real robot
- optimal control
- transfer learning
- computational intelligence
- supervised learning
- learning algorithm