arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.10442cs.AIcs.LG
收藏

释放深层反事实价值网络的潜力

Unlocking the Potential of Deep Counterfactual Value Networks

Minimal AI;Facebook AI Research(Facebook 人工智能研究院)

Ryan Zarick, Bryan Pellegrino, Noam Brown, Caleb Banister

摘要:

深度反事实价值网络与持续解析相结合,提供了一种在信息博弈中进行深度有限搜索的方法。然而,自从在DeepStack扑克AI中引入以来,深度反事实价值网络还没有被广泛采用。在本文中,我们介绍了对深度反事实价值网络的几项改进,以及反事实遗憾最小化,并分析了每项变化的影响。我们结合这些改进来创建扑克AI Supremus。我们表明,虽然DeepStack的重新实现在强大的基准代理Slumbot上失去了正面竞争,但Supremus成功地以极大的优势击败了Slumbot,并且在本地最佳响应中实现了比DeepStack更低的可利用性。总之,这些结果表明,通过我们的关键改进,深度反事实价值网络可以实现最先进的性能。

英文摘要:

Deep counterfactual value networks combined with continual resolving provide a way to conduct depth-limited search in imperfect-information games. However, since their introduction in the DeepStack poker AI, deep counterfactual value networks have not seen widespread adoption. In this paper we introduce several improvements to deep counterfactual value networks, as well as counterfactual regret minimization, and analyze the effects of each change. We combined these improvements to create the poker AI Supremus. We show that while a reimplementation of DeepStack loses head-to-head against the strong benchmark agent Slumbot, Supremus successfully beats Slumbot by an extremely large margin and also achieves a lower exploitability than DeepStack against a local best response. Together, these results show that with our key improvements, deep counterfactual value networks can achieve state-of-the-art performance.

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。

↑