Approximating Ergodic Average Reward Continuous-Time Controlled Markov Chains.
Tomás Prieto-RumeauJosé María LorenzoPublished in: IEEE Trans. Autom. Control. (2010)
Keyphrases
- markov chain
- average reward
- stationary distribution
- steady state
- markov processes
- markov process
- semi markov decision processes
- sample path
- transition probabilities
- state space
- random walk
- finite state
- monte carlo
- stochastic process
- markov model
- markov decision processes
- discounted reward
- transition matrix
- optimal policy
- hierarchical reinforcement learning
- probabilistic automata
- data mining