arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.03057cs.GTcs.AI
收藏

基于基线的扩展型博弈蒙特卡罗反事实遗憾最小化(VR-MCCFR)的方差缩减

Variance Reduction in Monte Carlo Counterfactual Regret Minimization (VR-MCCFR) for Extensive Form Games using Baselines

DeepMind(深度思维);University of Alberta(阿尔伯塔大学)

Martin Schmid, Neil Burch, Marc Lanctot, Matej Moravcik, Rudolf Kadlec, Michael Bowling

摘要:

从交互样本中学习不完全信息博弈策略是一个具有挑战性的问题。这种情况下的一种常用方法,蒙特卡罗反事实后悔最小化(MCCFR),由于方差很大,长期收敛速度很慢。在本文中,我们介绍了一种方差减少技术(VR-MCCFR),适用于任何采样变量的MCCFR。使用这种技术,每次迭代的估计值和更新被重新制定为采样值和状态动作基线的函数,类似于它们在策略梯度强化学习中的使用。新的公式允许从同一事件中的其他估计中自举估计,沿着采样轨迹传播基线的好处;即使从其他估计中自举,估计仍然是无偏的。最后,我们表明,给定一个完美的基线,值估计的方差可以减少到零。实验结果表明,VR-MCCFR带来了一个数量级的加速,而经验方差减少了三个数量级。降低的方差允许CFR+首次与采样一起使用,将加速提高到两个数量级。

英文摘要:

Learning strategies for imperfect information games from samples of interaction is a challenging problem. A common method for this setting, Monte Carlo Counterfactual Regret Minimization (MCCFR), can have slow long-term convergence rates due to high variance. In this paper, we introduce a variance reduction technique (VR-MCCFR) that applies to any sampling variant of MCCFR. Using this technique, per-iteration estimated values and updates are reformulated as a function of sampled values and state-action baselines, similar to their use in policy gradient reinforcement learning. The new formulation allows estimates to be bootstrapped from other estimates within the same episode, propagating the benefits of baselines along the sampled trajectory; the estimates remain unbiased even when bootstrapping from other estimates. Finally, we show that given a perfect baseline, the variance of the value estimates can be reduced to zero. Experimental evaluation shows that VR-MCCFR brings an order of magnitude speedup, while the empirical variance decreases by three orders of magnitude. The decreased variance allows for the first time CFR+ to be used with sampling, increasing the speedup to two orders of magnitude.

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。

↑