Markov Chain Concentration with an Application in Reinforcement Learning.
Debangshu BanerjeePublished in: CoRR (2023)
Keyphrases
- markov chain
- reinforcement learning
- state space
- steady state
- monte carlo method
- transition probabilities
- finite state
- markov model
- markov process
- monte carlo
- stochastic process
- stationary distribution
- monte carlo simulation
- random walk
- learning algorithm
- machine learning
- optimal policy
- markov decision processes
- dynamic programming
- transfer learning
- supervised learning
- markov models
- optimal control
- least squares
- transition matrix