Monte-Carlo Go Reinforcement Learning Experiments.
Bruno BouzyGuillaume ChaslotPublished in: CIG (2006)
Keyphrases
- monte carlo
- reinforcement learning
- temporal difference
- stochastic approximation
- policy evaluation
- markov chain
- monte carlo simulation
- importance sampling
- temporal difference learning
- reinforcement learning algorithms
- monte carlo methods
- monte carlo tree search
- state space
- adaptive sampling
- function approximation
- model free
- matrix inversion
- monte carlo method
- learning algorithm
- optimal strategy
- function approximators
- simulation study
- supervised learning
- machine learning
- markovian decision
- policy iteration
- control problems
- markov decision processes
- computational cost
- learning process