Learning to Plan via Deep Optimistic Value Exploration.
Tim SeydeWilko SchwartingSertac KaramanDaniela RusPublished in: L4DC (2020)
Keyphrases
- learning algorithm
- inductive inference
- learning systems
- learning process
- learning scheme
- supervised learning
- autonomous learning
- knowledge acquisition
- online learning
- data sets
- artificial intelligence
- information retrieval
- active learning
- reinforcement learning
- training data
- dynamic environments
- feature selection
- information systems
- deep learning
- action models