Archie C. Chapman, David S. Leslie, Alex Rogers, Nicholas R. Jennings. Convergent Learning Algorithms for Unknown Reward Games. SIAM J. Control and Optimization, 51(4):3154-3180, 2013. [doi]
@article{ChapmanLRJ13, title = {Convergent Learning Algorithms for Unknown Reward Games}, author = {Archie C. Chapman and David S. Leslie and Alex Rogers and Nicholas R. Jennings}, year = {2013}, doi = {10.1137/120893501}, url = {http://dx.doi.org/10.1137/120893501}, researchr = {https://researchr.org/publication/ChapmanLRJ13}, cites = {0}, citedby = {0}, journal = {SIAM J. Control and Optimization}, volume = {51}, number = {4}, pages = {3154-3180}, }