Sequential and Dynamic constraint Contrastive Learning for Reinforcement Learning.
Weijie ShenLei YuanJunfu HuangSongyi GaoYuyang HuangYang YuPublished in: IJCNN (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- supervised learning
- learning problems
- inductive inference
- learning tasks
- online learning
- autonomous learning
- action selection
- learning systems
- dynamic environments
- active learning
- mobile devices
- unsupervised learning
- prior knowledge
- learning scenarios
- solving problems
- decision trees
- function approximators
- learning agents
- reinforcement learning methods
- genetic algorithm