Exponential Convergence in Undiscounted Continuous-Time Markov Decision Chains.
W. H. M. ZijmPublished in: Math. Oper. Res. (1987)
Keyphrases
- markov decision chains
- iterative learning control
- risk sensitive
- average cost
- markov decision processes
- optimal control
- markov chain
- infinite horizon
- markov processes
- stationary policies
- finite state
- state space
- machine learning
- bayesian networks
- convergence rate
- policy iteration
- average reward
- finite horizon
- stochastic games
- markov decision problems
- probability distribution