Abhijit Gosavi. Reinforcement learning for long-run average cost. European Journal of Operational Research, 155(3):654-674, 2004. [doi]
@article{Gosavi04:0, title = {Reinforcement learning for long-run average cost}, author = {Abhijit Gosavi}, year = {2004}, doi = {10.1016/S0377-2217(02)00874-3}, url = {http://dx.doi.org/10.1016/S0377-2217(02)00874-3}, researchr = {https://researchr.org/publication/Gosavi04%3A0}, cites = {0}, citedby = {0}, journal = {European Journal of Operational Research}, volume = {155}, number = {3}, pages = {654-674}, }