Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning.
Haotian FuHongyao TangJianye HaoChen ChenXidong FengDong LiWulong LiuPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- supervised learning
- learning problems
- effective learning
- knowledge acquisition
- learning systems
- contextual information
- optimal control
- evolutionary learning
- neural network
- temporal difference learning
- inductive inference
- mobile learning
- unsupervised learning
- active learning
- prior knowledge
- multi agent