We introduce the Laser Learning Environment (LLE), a collaborative
multi-agent reinforcement learning environment in which coordination is
central. In LLE, agents depend on each other to make progress
(interdependence), must jointly take specific sequences of actions to succeed
(perfect coordination), and accomplishing those joint actions does not yield
any intermediate reward (zero-incentive dynamics). The challenge of such
problems lies in the difficulty of escaping state space bottlenecks caused by
interdependence steps since escaping those bottlenecks is not rewarded. We test
multiple state-of-the-art value-based MARL algorithms against LLE and show that
they consistently fail at the collaborative task because of their inability to
escape state space bottlenecks, even though they successfully achieve perfect
coordination. We show that Q-learning extensions such as prioritized experience
replay and n-steps return hinder exploration in environments with
zero-incentive dynamics, and find that intrinsic curiosity with random network
distillation is not sufficient to escape those bottlenecks. We demonstrate the
need for novel methods to solve this problem and the relevance of LLE as
cooperative MARL benchmark.

我们介绍了 Laser Learning Environment (LLE)，它是一个协作的多主体强化学习环境，其中协调是中心。在 LLE 中，代理依靠彼此进行进展（相互依赖性），必须共同采取特定的行动序列才能成功（完美协调），并且完成这些共同行动不会产生任何中间奖励（零激励动态）。这类问题的挑战在于难以摆脱由相互依赖步骤引起的状态空间瓶颈，因为摆脱这些瓶颈没有受到奖励。我们对多个最先进的基于值的 MARL 算法在 LLE 上进行测试，并表明它们在协作任务上始终失败，因为它们无法摆脱状态空间瓶颈，尽管它们成功实现了完美协调。我们显示 Q-learning 的扩展方法，如优先经验回放和 n 步回报，阻碍了在具有零激励动态的环境中的探索，并发现奇妙的好奇心结合随机网络提取不足以摆脱那些瓶颈。我们展示了解决这个问题的新方法的需求以及 LLE 作为合作 MARL 基准的相关性。

激光学习环境：用于协调关键多智能体任务的新环境

Laser Learning Environment: A new environment for coordination-critical  multi-agent tasks

We used natural language processing to analyze a billion words to study
cultural differences on Weibo, one of China's largest social media platforms.
We compared predictions from two common explanations about cultural differences
in China (economic development and urban-rural differences) against the
less-obvious legacy of rice versus wheat farming. Rice farmers had to
coordinate shared irrigation networks and exchange labor to cope with higher
labor requirements. In contrast, wheat relied on rainfall and required half as
much labor. We test whether this legacy made southern China more
interdependent. Across all word categories, rice explained twice as much
variance as economic development and urbanization. Rice areas used more words
reflecting tight social ties, holistic thought, and a cautious, prevention
orientation. We then used Twitter data comparing prefectures in Japan, which
largely replicated the results from China. This provides crucial evidence of
the rice theory in a different nation, language, and platform.

利用自然语言处理分析了十亿个字，来研究中国最大的社交媒体平台之一微博上的文化差异。比较了关于中国文化差异的两种常见解释（经济发展和城乡差异），并与不那么明显的稻谷种植与小麦种植的遗留影响进行对比。稻谷种植地区使用了更多反映紧密社会关系、整体性思维和谨慎、预防导向的词汇，从而测试这种遗留影响是否使中国南方更加相互依存。通过对日本的推特数据进行比较，得到了与中国几乎相同的结果，从而为稻谷理论提供了重要证据。

中国和 日本现代语言使用的历史稻田模式解释胜过现代化和城市化

Historical patterns of rice farming explain modern-day language use in  China and Japan more than modernization and urbanization

We propose a modeling framework for growing multiplexes where a node can
belong to different networks. We define new measures for multiplexes and we
identify a number of relevant ingredients for modeling their evolution such as
the coupling between the different layers and the arrival time distribution of
nodes. The topology of the multiplex changes significantly in the different
cases under consideration, with effects of the arrival time of nodes on the
degree distribution, average shortest paths and interdependence.

提出一种多重网络的建模框架，其中节点可以属于不同的网络，并定义了新的多重网络的度量标准以及模拟它们演化的相关影响因素，如不同层之间的耦合和节点到达时间分布等。节点的到达时间对于网络的拓扑结构的演变产生了显著影响，尤其是在度分布、平均最短路径和相互依赖性方面。