arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.07166cs.AIcs.LGcs.MA
收藏

Hanabi中Zero-Shot协调的K级推理

K-level Reasoning for Zero-Shot Coordination in Hanabi

Facebook AI Research(脸书人工智能研究院);University of Oxford(牛津大学)

Brandon Cui, Hengyuan Hu, Luis Pineda, Jakob N. Foerster

摘要:

在合作的多代理设置的标准问题设置是自我发挥(SP),其目标是训练一个团队的代理一起工作。然而,最佳SP策略通常包含任意约定(“握手”),并且与其他独立训练的代理或人类不兼容。后一种需求最近由Hu等人(2020)正式定义为zero-shot协调(ZSC)设置,并部分通过他们的模拟游戏(OP)算法解决,该算法在纸牌游戏Hanabi中显示了改进的ZSC和人类AI性能。OP假设可以访问环境的对称性,并防止代理在训练期间以相互不兼容的方式破坏这些对称性。然而,正如作者所指出的,发现给定环境的对称性是一个计算上的难题。相反,我们表明,通过简单的k级推理(KLR)Costa Gomes et al. 2006,同步训练所有级别,我们可以在Hanabi中获得有竞争力的ZSC和ad-hoc团队合作性能,包括与类人代理机器人配对时。我们还介绍了一种新的方法,同步k级推理与最佳响应(SyKLRBR),它进一步提高了我们的同步KLR的性能,通过共同训练的最佳响应。

英文摘要:

The standard problem setting in cooperative multi-agent settings is self-play (SP), where the goal is to train a team of agents that works well together. However, optimal SP policies commonly contain arbitrary conventions ("handshakes") and are not compatible with other, independently trained agents or humans. This latter desiderata was recently formalized by Hu et al. 2020 as the zero-shot coordination (ZSC) setting and partially addressed with their Other-Play (OP) algorithm, which showed improved ZSC and human-AI performance in the card game Hanabi. OP assumes access to the symmetries of the environment and prevents agents from breaking these in a mutually incompatible way during training. However, as the authors point out, discovering symmetries for a given environment is a computationally hard problem. Instead, we show that through a simple adaption of k-level reasoning (KLR) Costa Gomes et al. 2006, synchronously training all levels, we can obtain competitive ZSC and ad-hoc teamplay performance in Hanabi, including when paired with a human-like proxy bot. We also introduce a new method, synchronous-k-level reasoning with a best response (SyKLRBR), which further improves performance on our synchronous KLR by co-training a best response.

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。

↑