Abstract
Credit Assignment is a crucial ingredient for successful Adap-
tive Operator Selection. Instead of the average fitness improvement of
newborn offspring, this paper proposes to use some empirical order statis-
tics of those improvements, arguing that rare but highly beneficial jumps
matter as much or more than frequent but small improvements. An ex-
treme value based Credit Assignment is thus proposed, rewarding each
operator with the best fitness improvement observed in a sliding window
for this operator. This mechanism, combined with existing Adaptive Op-
erator Selection rules, is investigated in an EC-like setting. First results
show that the proposed method allows both the Adaptive Pursuit and
the Dynamic Multi-Armed Bandit selection rules to actually track the
best operators along evolution.
Users
Please
log in to take part in the discussion (add own reviews or comments).