Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots.
Wei HungBo-Kai HuangPing-Chun HsiehXi LiuPublished in: CoRR (2022)
Keyphrases
- multi objective
- reinforcement learning
- optimization algorithm
- evolutionary algorithm
- memory usage
- information sharing
- multi objective optimization
- genetic algorithm
- learning algorithm
- feature selection
- objective function
- multiobjective optimization
- multiple objectives
- particle swarm optimization
- sample size
- neural network
- computational complexity
- memory requirements
- cost sensitive
- knowledge sharing
- high efficiency
- nsga ii
- model free
- multi agent
- conflicting objectives