(The convergent drive would be to tit-for-tat until you observe enough to solve the POMDP of them, betraying/​exploiting them maximally the instant you gather enough info to decide that is more rewarding...)
(The convergent drive would be to tit-for-tat until you observe enough to solve the POMDP of them, betraying/​exploiting them maximally the instant you gather enough info to decide that is more rewarding...)