Warmth and competence in human-agent cooperation

arXiv:2201.13448v3 Announce Type: replace-cross
Abstract: Interaction and cooperation with humans are overarching aspirations of artificial intelligence (AI) research. Recent studies demonstrate that AI agents trained with deep reinforcement learning are capable of collaborating with humans. These studies primarily evaluate human compatibility through "objective" metrics such as task performance, obscuring potential variation in the levels of trust and subjective preference that different agents garner. To better understand the factors shaping subjective preferences in human-agent cooperation, we train deep reinforcement learning agents …

abstract agent agents ai agents artificial artificial intelligence arxiv cs.cy cs.hc cs.lg human humans intelligence metrics performance reinforcement reinforcement learning research studies through type variation