通过利用共同信号改善合作
Improved Cooperation by Exploiting a Common Signal
摘要：
人工智能体能从人类习俗中获益吗？尽管非合作博弈论的预言很悲观，但人类社会成功地自我组织起来，解决了公共资源的悲剧。最重要的是，现实世界的问题本质上是大规模的，可观察性低。在这种情况下，促进人类协调的一个关键概念是使用约定。受人类行为的启发，我们研究了学习动态和时间惯例的出现，重点是公共资源。在设计一个现实的评估环境中给予了额外的强调：（a）环境动态是以现实世界的渔业为模型的，（b）我们假设分散学习，代理只能观察自己的历史，（c）我们运行大规模模拟（多达64个代理）。非耦合策略和低可观测性使得合作难以实现;随着代理数量的增长，采取正确梯度方向的概率呈指数下降。通过引入任意公共信号（例如，日期，时间，或任何周期性的一组数字）作为一种手段来耦合的学习过程中，我们表明，时间惯例可以出现和代理达到可持续的收获策略。信号的引入持续改善了社会福利（平均258%，最高达3306%），可实现可持续性的环境参数范围（平均46%，最高达300%），以及低丰度环境中的收敛速度（平均13%，最高达53%）。
英文摘要：
Can artificial agents benefit from human conventions? Human societies manage to successfully self-organize and resolve the tragedy of the commons in common-pool resources, in spite of the bleak prediction of non-cooperative game theory. On top of that, real-world problems are inherently large-scale and of low observability. One key concept that facilitates human coordination in such settings is the use of conventions. Inspired by human behavior, we investigate the learning dynamics and emergence of temporal conventions, focusing on common-pool resources. Extra emphasis was given in designing a realistic evaluation setting: (a) environment dynamics are modeled on real-world fisheries, (b) we assume decentralized learning, where agents can observe only their own history, and (c) we run large-scale simulations (up to 64 agents). Uncoupled policies and low observability make cooperation hard to achieve; as the number of agents grow, the probability of taking a correct gradient direction decreases exponentially. By introducing an arbitrary common signal (e.g., date, time, or any periodic set of numbers) as a means to couple the learning process, we show that temporal conventions can emerge and agents reach sustainable harvesting strategies. The introduction of the signal consistently improves the social welfare (by 258% on average, up to 3306%), the range of environmental parameters where sustainability can be achieved (by 46% on average, up to 300%), and the convergence speed in low abundance settings (by 13% on average, up to 53%).
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。
