人机合作中的温暖与能力
Warmth and competence in human-agent cooperation
AI总结：
本文在Coins社会困境中研究501名参与者对深度强化学习智能体的合作偏好，发现温暖与能力感知比客观任务表现更能预测陈述偏好和显示偏好。
摘要：
与人类互动和合作是人工智能（AI）研究的总体愿景。近期研究表明，使用深度强化学习训练的AI智能体能够与人类协作。这些研究主要通过任务表现等“客观”指标评估人类兼容性，从而掩盖了不同智能体所获得的信任程度和主观偏好可能存在的差异。为了更好地理解塑造人机合作中主观偏好的因素，我们在双人社会困境Coins中训练深度强化学习智能体。我们招募了N=501名参与者开展一项人机合作研究，并测量他们对所遇到智能体的印象。参与者对温暖和能力的感知能够预测他们对不同智能体的陈述偏好，其预测力超出客观表现指标。受社会科学和生物学研究启发，我们随后实施了一个新的“伙伴选择”框架，以引致显示偏好：在与某个智能体玩完一个回合后，参与者被询问是否愿意与同一智能体继续下一回合，还是独自游玩。与陈述偏好一样，社会感知对参与者显示偏好的预测优于客观表现。基于这些结果，我们建议人机交互研究者在研究中常规纳入对社会感知和主观偏好的测量。
英文摘要：
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 in Coins, a two-player social dilemma. We recruit $N = 501$ participants for a human-agent cooperation study and measure their impressions of the agents they encounter. Participants' perceptions of warmth and competence predict their stated preferences for different agents, above and beyond objective performance metrics. Drawing inspiration from social science and biology research, we subsequently implement a new ``partner choice'' framework to elicit revealed preferences: after playing an episode with an agent, participants are asked whether they would like to play the next episode with the same agent or to play alone. As with stated preferences, social perception better predicts participants' revealed preferences than does objective performance. Given these results, we recommend human-agent interaction researchers routinely incorporate the measurement of social perception and subjective preferences into their studies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
