Learning is planning: near Bayes-optimal reinforcement learning via Monte-Carlo tree search
John AsmuthMichael L. LittmanPublished in: CoRR (2012)
Keyphrases
- reinforcement learning
- learning algorithm
- bayes optimal
- monte carlo tree search
- reinforcement learning methods
- bayesian reinforcement learning
- learning curve
- action selection
- version space
- markov decision processes
- function approximation
- temporal difference learning
- learning process
- learning problems
- optimal control
- supervised learning
- active learning
- monte carlo
- model free
- upper bound
- state space
- machine learning