Information Directed Reward Learning for Reinforcement Learning.
David LindnerMatteo TurchettaSebastian TschiatschekKamil CiosekAndreas KrausePublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning process
- prior knowledge
- learning algorithm
- eligibility traces
- previously learned
- function approximators
- supervised learning
- actor critic
- information sources
- learning systems
- background knowledge
- function approximation
- machine learning
- dynamic programming
- autonomous learning
- keywords
- learned knowledge
- state action
- multi agent
- partially observable
- learning capabilities
- reinforcement learning algorithms
- reward function
- learning tasks
- information sharing
- transfer learning
- mobile learning
- information processing
- online learning
- collaborative learning