Learning a Belief Representation for Delayed Reinforcement Learning.
Pierre LiotetErick VenneriMarcello RestelliPublished in: IJCNN (2021)
Keyphrases
- reinforcement learning
- learning process
- learning problems
- online learning
- learning algorithm
- prior knowledge
- active learning
- supervised learning
- temporal difference learning
- autonomous learning
- continuous state
- inductive inference
- learning tasks
- background knowledge
- learning experience
- learning systems
- image representation
- unsupervised learning
- knowledge acquisition