On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning.
Che WangKeith W. RossPublished in: CoRR (2020)
Keyphrases
- monte carlo
- stochastic approximation
- reinforcement learning
- dynamic programming
- importance sampling
- monte carlo simulation
- markov chain
- simulation study
- iterative algorithms
- detection algorithm
- expectation maximization
- learning algorithm
- convergence rate
- worst case
- markov chain monte carlo
- computational complexity
- objective function
- matrix inversion
- monte carlo methods
- monte carlo tree search
- kalman filter
- temporal difference
- least squares
- adaptive sampling
- markovian decision