Warmth and competence in human-agent cooperation

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 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.

Accepted at Autonomous Agents and Multi-Agent Systems

References in corpus (9)

• Artificial Intelligence: the global landscape of ethics guidelines
• Skillful Precipitation Nowcasting using Deep Generative Models of Radar
• Multi-agent Reinforcement Learning in Sequential Social Dilemmas
• Conceptual Metaphors Impact Perceptions of Human-AI Collaboration
• Exciting, Useful, Worrying, Futuristic: Public Perception of Artificial Intelligence in 8 Countries
• On the Utility of Learning about Humans for Human-AI Coordination
• Environmental drivers of systematicity and generalization in a situated agent
• Warmth and Competence to Predict Human Preference of Robot Behavior in Physical Human-Robot Interaction
• Quantifying the effects of environment and population diversity in multi-agent reinforcement learning

Cited by in corpus (1)

• Asymmetric interaction preference induces cooperation in human-agent hybrid game