Langevin Monte Carlo for Contextual Bandits.
Pan XuHongkai ZhengEric MazumdarKamyar AzizzadenesheliAnima AnandkumarPublished in: CoRR (2022)
Keyphrases
- monte carlo
- markov chain
- monte carlo simulation
- importance sampling
- monte carlo tree search
- simulation study
- monte carlo method
- stochastic approximation
- monte carlo methods
- markovian decision
- adaptive sampling
- particle filter
- global illumination
- variance reduction
- temporal difference
- optimal strategy
- objective function
- bayesian networks
- simulated annealing
- state space
- uct algorithm