Learning against multiple opponents

21 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Empirically Evaluating Multiagent Learning Algorithms (2014, methodology): “is setting instead of n-player repeated games or either2- orn-player stochastic games for two reasons. First, the case of two-player repeated games has received the most past study (though see e.g., (Vu et al., 2005)). Second, considerably more work has been done to identify experimentally-interesti”
Opportunities for multiagent systems and multiagent reinforcement learning in traffic control (2009, background): “Although other criteria are being proposed (see [86]), it certainly makes little sense to evaluate a learning or adaptation algorithm by such criteria when the environment is itself dynamic, as it is the case of the traffic scenario discussed here.”