学会不沟通地聚集
Learning to Gather without Communication
摘要:
关于新兴集体行为的一个标准信念是,它源于简单的个人规则。大多数关于这种集体行为的数学研究都是从强制性的个体规则开始的,比如总是去中心。但是,如何在群体生命周期的短时间内出现(最佳)个人规则,特别是在沟通不可用的情况下。我们认为,这样的规则实际上可以通过集体(多智能体)强化学习,即通过奖励和惩罚的学习,在很短的时间内出现在一个群体中。我们考虑聚集问题:几个代理(社会动物,群集机器人......)必须聚集在同一位置,这不是事先确定的。他们必须这样做,而不需要就他们的计划决策进行沟通,只需查看其他代理人的位置。我们提出的第一个实验证据表明,一个收集的行为可以学习,而无需在部分可观察的环境中进行通信。学习到的行为与自稳定分布式算法具有相同的属性,因为进程可以从任何初始状态收集(从而容忍任何瞬时故障)。此外,我们表明,它是可以容忍高达90%的代理人的残酷损失,而不会对行为产生重大影响。
英文摘要:
A standard belief on emerging collective behavior is that it emerges from simple individual rules. Most of the mathematical research on such collective behavior starts from imperative individual rules, like always go to the center. But how could an (optimal) individual rule emerge during a short period within the group lifetime, especially if communication is not available. We argue that such rules can actually emerge in a group in a short span of time via collective (multi-agent) reinforcement learning, i.e learning via rewards and punishments. We consider the gathering problem: several agents (social animals, swarming robots...) must gather around a same position, which is not determined in advance. They must do so without communication on their planned decision, just by looking at the position of other agents. We present the first experimental evidence that a gathering behavior can be learned without communication in a partially observable environment. The learned behavior has the same properties as a self-stabilizing distributed algorithm, as processes can gather from any initial state (and thus tolerate any transient failure). Besides, we show that it is possible to tolerate the brutal loss of up to 90\% of agents without significant impact on the behavior.
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。