Dynamic analysis of multiagent <i>Q</i>-learning with ε-greedy exploration.

Eduardo Rodrigues Gomes Ryszard Kowalczyk Dynamic analysis of multiagent <i>Q</i>-learning with ε-greedy exploration. 47 2009 ICML http://doi.acm.org/10.1145/1553374.1553422 conf/icml/2009 db/conf/icml/icml2009.html#GomesK09