Combining a gradient-based method and an evolution strategy for multi-objective reinforcement learning.
Diqi ChenYizhou WangWen GaoPublished in: Appl. Intell. (2020)
Keyphrases
- evolution strategy
- multi objective
- reinforcement learning
- optimization algorithm
- dynamic programming
- objective function
- cost function
- significant improvement
- evolutionary algorithm
- pairwise
- high accuracy
- preprocessing
- differential evolution
- learning algorithm
- worst case
- optimization process
- optimal solution
- model free