High Confidence Generalization for Reinforcement Learning.
James KostasYash ChandakScott M. JordanGeorgios TheocharousPhilip S. ThomasPublished in: ICML (2021)
Keyphrases
- high confidence
- reinforcement learning
- association rules
- state space
- model free
- function approximation
- machine learning
- multi agent
- data analysis
- dynamic programming
- data mining
- temporal difference
- markov decision processes
- learning machines
- policy search
- multi agent reinforcement learning
- optimal control
- learning problems
- transfer learning
- class labels
- optimal policy
- principal component analysis
- supervised learning