On the convergence of reinforcement learning with Monte Carlo Exploring Starts.
Jun LiuPublished in: Autom. (2021)
Keyphrases
- monte carlo
- stochastic approximation
- reinforcement learning
- temporal difference
- monte carlo simulation
- markov chain
- policy evaluation
- importance sampling
- simulation study
- state space
- markovian decision
- temporal difference learning
- monte carlo method
- particle filter
- monte carlo methods
- adaptive sampling
- optimal strategy
- variance reduction
- matrix inversion
- monte carlo tree search
- function approximation
- model free
- convergence speed
- convergence rate
- optimal policy
- global illumination
- simulated annealing