Wrobel, A. On Markovian Decision Models with a Finite Skeleton. Mathematical Methods of Operations Research (ZOR). 1984, 28 (February): 17–27. S2CID 2545336. doi:10.1007/bf01919083.
Kearns, Michael; Mansour, Yishay; Ng, Andrew. A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes. Machine Learning. 2002, 49 (193–208): 193–208. doi:10.1023/A:1017932429737.
Wrobel, A. On Markovian Decision Models with a Finite Skeleton. Mathematical Methods of Operations Research (ZOR). 1984, 28 (February): 17–27. S2CID 2545336. doi:10.1007/bf01919083.