1. Policy-gradient algorithms for partially observable Markov decision processes;Aberdeen,2003
2. Learning algorithms for Markov decision processes with average cost;Abounadi;SIAM Journal on Control and Optimization,2002
3. Statistical predictor identification;Akaike;Annals of the Institute of Statistical Mathematics,1970
4. Information theory and an extension of the maximum likelihood principle;Akaike,1973
5. A new look at the statistical model identification;Akaike;IEEE Transactions on Automatic Control,1974