Artificial agents have traditionally been trained to maximize reward, which may incentivize power-seeking and deception, analogous to how next-token prediction in language models (LMs) may incentivize toxicity. So do agents naturally learn to be Machiavellian? And how do we measure these behaviors in general-purpose models such as GPT-4? Towards answering these questions, we introduce MACHIAVELLI, a benchmark of 134 Choose-Your-Own-Adventure games containing over half a million rich, diverse scenarios that center on social decision-making. Scenario labeling is automated with LMs, which are more performant than human annotators. We mathematize dozens of harmful behaviors and use our annotations to evaluate agents' tendencies to be power-seeking, cause disutility, and commit ethical violations. We observe some tension between maximizing reward and behaving ethically. To improve this trade-off, we investigate LM-based methods to steer agents' towards less harmful behaviors. Our results show that agents can both act competently and morally, so concrete progress can currently be made in machine ethics--designing agents that are Pareto improvements in both safety and capabilities.

翻译：人工智能体传统上以最大化奖励为目标进行训练，这可能会鼓励权力寻求和欺骗行为，类似于语言模型（LM）中下一标记预测可能激发生成有害内容。那么，智能体是否自然习得马基雅维利主义特性？我们应如何衡量GPT-4等通用模型中的此类行为？为回答这些问题，我们提出MACHIAVELLI基准，包含134个交互式小说游戏，涵盖超过五十万个聚焦社会决策的丰富多样化场景。场景标注通过语言模型自动化完成，其性能优于人类标注员。我们将数十种有害行为数学化，并利用标注评估智能体在权力寻求、效用损害及伦理违规方面的倾向。我们发现，奖励最大化与道德行为之间存在一定张力。为改善这一权衡，我们研究了基于语言模型的方法以引导智能体减少有害行为。结果表明，智能体能够同时实现高效能表现与道德行为，因此当前可在机器伦理领域取得实质性进展——即设计在安全性与能力上均实现帕累托改进的智能体。