Combiner connaissances expertes, hors-ligne, transientes et en ligne pour l'exploration Monte-Carlo. Apprentissage et MC.
Guillaume ChaslotL. ChatriotChristophe FiterSylvain GellyJean-Baptiste HoockJulien PerezArpad RimmelOlivier TeytaudPublished in: Rev. d'Intelligence Artif. (2009)
Keyphrases
- monte carlo
- markov chain
- monte carlo simulation
- importance sampling
- monte carlo methods
- adaptive sampling
- particle filter
- simulation study
- monte carlo tree search
- stochastic approximation
- computational cost
- uct algorithm
- monte carlo method
- temporal difference
- markovian decision
- matrix inversion
- machine learning
- action selection
- learning algorithm