风险多样性下的学习集体行动
Learning Collective Action under Risk Diversity
摘要：
集体风险困境（CRD）是一类代表社会挑战的n人游戏，其中群体需要协调以避免灾难性结果的风险。多智能体系统面临这样的困境，实现合作的困难，往往收敛到次优，风险主导的解决方案，每个人的缺陷。在本文中，我们研究的后果，风险多样性的代理学习发挥CRD组。我们发现，风险多样性的地方，在同质群体中没有观察到的合作新的挑战。我们发现，增加风险的多样性显着降低整体合作，并阻碍集体目标的实现。它导致代理人政策的不对称变化-即高风险个人缴款的增加无法弥补低风险个人缴款的减少-总体上减少了总体缴款总额。当将RL行为与理性的个人主义和社会行为进行比较时，我们发现RL种群收敛于代理之间的更公平的贡献。我们的研究结果强调，需要调整代理人之间的风险认知或开发新的学习技术，明确考虑到风险的多样性。
英文摘要：
Collective risk dilemmas (CRDs) are a class of n-player games that represent societal challenges where groups need to coordinate to avoid the risk of a disastrous outcome. Multi-agent systems incurring such dilemmas face difficulties achieving cooperation and often converge to sub-optimal, risk-dominant solutions where everyone defects. In this paper we investigate the consequences of risk diversity in groups of agents learning to play CRDs. We find that risk diversity places new challenges to cooperation that are not observed in homogeneous groups. We show that increasing risk diversity significantly reduces overall cooperation and hinders collective target achievement. It leads to asymmetrical changes in agents' policies -- i.e. the increase in contributions from individuals at high risk is unable to compensate for the decrease in contributions from individuals at low risk -- which overall reduces the total contributions in a population. When comparing RL behaviors to rational individualistic and social behaviors, we find that RL populations converge to fairer contributions among agents. Our results highlight the need for aligning risk perceptions among agents or develop new learning techniques that explicitly account for risk diversity.
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。
