Maozu Guo, Yang Liu, Jacek Malec. A new Q-learning algorithm based on the metropolis criterion. IEEE Transactions on Systems, Man, and Cybernetics, Part A, 34(5):2140-2143, 2004. [doi]
@article{GuoLM04, title = {A new Q-learning algorithm based on the metropolis criterion}, author = {Maozu Guo and Yang Liu and Jacek Malec}, year = {2004}, doi = {10.1109/TSMCB.2004.832154}, url = {http://doi.ieeecomputersociety.org/10.1109/TSMCB.2004.832154}, tags = {rule-based}, researchr = {https://researchr.org/publication/GuoLM04}, cites = {0}, citedby = {0}, journal = {IEEE Transactions on Systems, Man, and Cybernetics, Part A}, volume = {34}, number = {5}, pages = {2140-2143}, }