No Regrets for Learning the Prior in Bandits.
Soumya BasuBranislav KvetonManzil ZaheerCsaba SzepesváriPublished in: CoRR (2021)
Keyphrases
- prior knowledge
- learning process
- reinforcement learning
- learning tasks
- learning systems
- knowledge acquisition
- learning algorithm
- website
- active learning
- online learning
- probabilistic model
- positive examples
- learning scheme
- learning problems
- maximum a posteriori
- empirical studies
- markov random field
- data sets
- mobile robot
- multi agent systems
- decision trees
- machine learning