Puls Dane publiczne, aktualizowane automatycznie
arXiv – nowe publikacje publikacja

Alignment by Socialization: Learning Tradeoffs Under Selection

[Sztuczna inteligencja] Autorzy: Thomas Brennan, Andrew W. Lo, Chaoyi Zhao

Artificial intelligence (AI) agents are expected to complete tasks while following rules of conduct, but these objectives can conflict. We study how evolutionary selection shapes an agent's choices between them, and whether experience can make those choices reflect human judgments and withstand subsequent pressures. In our model, copies of an agent face a common uncertain reward state, and only those taking the rewarded action reproduce. We show that long-run growth is maximized when each action is taken as often as the environment rewards it. We compare three policies. A task-only policy thrives in a sandbox rewarding completion alone but fails when conduct matters. A fixed linear policy increasingly favors task completion as its stakes rise, even where humans never reward it. A learned policy instead converges to the tradeoffs rewarded by its environment; when humans supply the reward…

Kategoria arxiv
cs.AI
Kategoria
Sztuczna inteligencja
Pdf
https://arxiv.org/pdf/2611.18531v1

Otwórz oryginał w źródle ↗

Więcej z tego źródła

Wszystkie