Two Online Learning Playout Policies in Monte Carlo Go: An Application of Win/Loss States.
Jacques BasalduaSam StewartJ. Marcos Moreno-VegaPeter D. DrakePublished in: IEEE Trans. Comput. Intell. AI Games (2014)
Keyphrases
- monte carlo
- online learning
- e learning
- markov chain
- monte carlo simulation
- optimal policy
- importance sampling
- markov decision problems
- monte carlo tree search
- monte carlo methods
- particle filter
- simulation study
- markovian decision
- transition probabilities
- initial state
- multimedia presentations
- monte carlo method
- adaptive sampling
- stochastic approximation
- global illumination
- dynamical systems
- quasi monte carlo
- state space
- temporal difference
- matrix inversion