A sufficient condition for the existence of an optimal policy with respect to the average cost criterion in markovian decision processes : Prepublication
暂无分享,去创建一个
[1] Arie Hordijk,et al. A counterexample in discounted dynamic programming , 1972 .
[2] S. Ross. NON-DISCOUNTED DENUMERABLE MARKOVIAN DECISION MODELS , 1968 .
[3] S. Ross,et al. An Example in Denumerable Decision Processes , 1968 .
[4] C. Derman,et al. A SOLUTION TO A COUNTABLE SYSTEM OF EQUATIONS ARISING IN MARKOVIAN DECISION PROCESSES. , 1966 .
[5] C. Derman. DENUMERABLE STATE MARKOVIAN DECISION PROCESSES: AVERAGE COST CRITERION. , 1966 .
[6] C. Derman. MARKOVIAN SEQUENTIAL CONTROL PROCESSES-DENUMERABLE STATE SPACE , 1965 .
[7] K. Chung. Markov Chains with Stationary Transition Probabilities , 1961 .
[8] H. Scheffé. A Useful Convergence Theorem for Probability Distributions , 1947 .
[9] Cyrus Derman,et al. Finite State Markovian Decision Processes , 1970 .