Monte-Carlo utility estimates for Bayesian reinforcement learning.
Christos DimitrakakisPublished in: CDC (2013)
Keyphrases
- monte carlo
- monte carlo tree search
- bayesian reinforcement learning
- importance sampling
- markov chain
- monte carlo simulation
- confidence intervals
- monte carlo methods
- utility function
- temporal difference
- adaptive sampling
- optimal policy
- evaluation function
- optimal strategy
- particle filter
- game tree
- multi agent
- computational complexity
- optimal solution