Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning.
Anusha NagabandiIgnasi ClaveraSimin LiuRonald S. FearingPieter AbbeelSergey LevineChelsea FinnPublished in: ICLR (Poster) (2019)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- supervised learning
- autonomous learning
- learning problems
- online learning
- learning systems
- real world environments
- temporal difference learning
- learning capabilities
- active learning
- prior knowledge
- unsupervised learning
- dynamic environments
- knowledge acquisition
- background knowledge
- transfer learning
- learning analytics
- optimal control
- learning mechanism
- learned knowledge
- multi agent
- machine learning
- evolutionary learning
- neural network