Can good learners always compensate for poor learners?

Can a good learner compensate for a poor learner when paired in a coordination game? Previous work has given an example where a special learning algorithm (FMQ) is capable of doing just that when paired with a specific less capable algorithm even in games which stump the poorer algorithm when paired with itself. In this paper, we argue that this result is not general. We give a straightforward extension to the coordination game in which FMQ cannot compensate for the lesser algorithm. We also provide other problematic pairings, and argue that another highquality algorithm cannot do so either.

• Type: Conference
• Year: 2006
• Where: ATAL
• Authors: Keith Sullivan, Liviu Panait, Gabriel Catalin Balan, Sean Luke
• Keywords: Algorithm, ATAL 2006, Coordination Game, Intelligent Agents, Special Learning Algorithm