On Reinforcement Learning Using Monte Carlo Tree Search with Supervised Learning: Non-Asymptotic Analysis.
Devavrat ShahQiaomin XieZhi XuPublished in: CoRR (2019)
Keyphrases
- asymptotic analysis
- monte carlo tree search
- reinforcement learning
- supervised learning
- temporal difference
- reinforcement learning methods
- bayesian reinforcement learning
- monte carlo
- temporal difference learning
- fluid model
- function approximation
- reinforcement learning algorithms
- evaluation function
- state space
- model free
- optimal policy
- learning algorithm
- machine learning
- control problems
- markov decision processes
- action selection
- learning tasks
- policy iteration
- transfer learning
- game tree
- function approximators
- semi supervised
- active learning
- training data
- neural network
- step size
- action space