论文信息 - Tests for Suboptimal Actions in Discounted Markov Programming

Tests for Suboptimal Actions in Discounted Markov Programming

A new test for suboptimal actions in discounted Markov decision problems is proposed. The test is discussed in relation to that of MacQueen and Porteus and preferred computational schemes are given.

N. Hastings | J. M. Mello

[1] W. Jewell. MARKOV-RENEWAL PROGRAMMING , 1962 .

[2] J. MacQueen. A MODIFIED DYNAMIC PROGRAMMING METHOD FOR MARKOVIAN DECISION PROBLEMS , 1966 .

[3] E. Denardo. CONTRACTION MAPPINGS IN THE THEORY UNDERLYING DYNAMIC PROGRAMMING , 1967 .

[4] Amedeo R. Odoni,et al. On Finding the Maximal Gain for Markov Decision Processes , 1969, Oper. Res..

[5] Evan L. Porteus. Some Bounds for Discounted Sequential Decision Processes , 1971 .