Xi-Ren Cao, Xianping Guo. Partially Observable Markov Decision Processes With Reward Information: Basic Ideas and Models. IEEE Trans. Automat. Contr., 52(4):677-681, 2007. [doi]
@article{CaoG07-0, title = {Partially Observable Markov Decision Processes With Reward Information: Basic Ideas and Models}, author = {Xi-Ren Cao and Xianping Guo}, year = {2007}, doi = {10.1109/TAC.2007.894520}, url = {http://dx.doi.org/10.1109/TAC.2007.894520}, researchr = {https://researchr.org/publication/CaoG07-0}, cites = {0}, citedby = {0}, journal = {IEEE Trans. Automat. Contr.}, volume = {52}, number = {4}, pages = {677-681}, }