To evaluate the role of individual recognition in the evolution of coo
peration, we formulated and analyzed a genetic algorithm model (EvCo)
for playing the Iterated Prisoner's Dilemma (IPD) game. Strategies com
pete against each other during each generation, and successful strateg
ies contribute more of their attributes to the next generation. Each s
trategy is encoded on a 'chromosome' that plays the IPD, responding to
the sequences of most recent responses by the interacting individuals
(chromosomes). The analysis reported in this paper considered differe
nt memory capabilities (one to five previous interactions), pairing co
ntinuities (pairs of individuals remain together for about one, two, f
ive, or 1000 consecutive interactions), and types of individual recogn
ition (recognition capability was maximal, nil, or allowed to evolve b
etween these limits). Analysis of the results focused on the frequency
of mutual cooperation in pairwise interactions (a good indicator of o
verall success in the IPD) and on the extent to which previous respons
es by the focal individual and its partner were associated with the pa
rtner's identity (individual recognition). Results indicated that a fi
xed, substantial amount of individual recognition could maintain high
levers of mutual cooperation even at low pairing continuities, and a s
ignificant but limited capability for individual recognition evolved u
nder selection. Recognition generally increased mutual cooperation mor
e when the recent responses of individuals other than the current part
ner were ignored. Titrating recognition memory under selection using a
fitness cost suggested that memory of the partner's previous response
s was more valuable than memory of the focal's previous responses. The
dynamics produced to date by EvCo are a step toward understanding the
evolution of social networks, for which additional benefits associate
d with group interactions must be incorporated.