DeepMind, Paris, France.
DeepMind, London, UK.
Nat Commun. 2020 Nov 5;11(1):5603. doi: 10.1038/s41467-020-19244-4.
Multiplayer games have long been used as testbeds in artificial intelligence research, aptly referred to as the Drosophila of artificial intelligence. Traditionally, researchers have focused on using well-known games to build strong agents. This progress, however, can be better informed by characterizing games and their topological landscape. Tackling this latter question can facilitate understanding of agents and help determine what game an agent should target next as part of its training. Here, we show how network measures applied to response graphs of large-scale games enable the creation of a landscape of games, quantifying relationships between games of varying sizes and characteristics. We illustrate our findings in domains ranging from canonical games to complex empirical games capturing the performance of trained agents pitted against one another. Our results culminate in a demonstration leveraging this information to generate new and interesting games, including mixtures of empirical games synthesized from real world games.
多人游戏长期以来一直被用作人工智能研究的试验台，恰当地称为人工智能的“果蝇”。传统上，研究人员专注于使用知名游戏来构建强大的代理。然而，通过对游戏及其拓扑景观进行特征描述，这一进展可以得到更好的体现。解决后一个问题可以帮助我们更好地理解代理，并确定代理在其训练过程中应该针对下一个游戏。在这里，我们展示了如何将网络度量应用于大规模游戏的响应图，从而创建游戏景观，量化不同大小和特征的游戏之间的关系。我们在从经典游戏到复杂的经验游戏的多个领域中展示了我们的发现，这些游戏都捕获了经过训练的代理相互竞争的性能。我们的结果最终展示了如何利用这些信息生成新的有趣的游戏，包括从真实世界游戏中合成的经验游戏的混合物。
