arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2107.09158cs.LGstat.ML
收藏

改进策略梯度搜索中的探索:在符号优化中的应用

Improving exploration in policy gradient search: Application to symbolic optimization

Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室)

Mikel Landajuela, Brenden K. Petersen, Soo K. Kim, Claudio P. Santiago, Ruben Glatt, T. Nathan Mundhenk, Jacob F. Pettit, Daniel M. Faissol

摘要:

许多设计用于自动化数学任务的机器学习策略利用神经网络来搜索数学符号的大型组合空间。与传统的进化方法相比,在搜索的核心使用神经网络允许学习更高级别的符号模式,提供明智的方向来指导搜索。当没有标记数据可用时,仍然可以使用强化学习来训练这样的网络。然而,我们证明,这种方法可以从早期的承诺现象和初始化偏差,这两个限制探索。我们提出了两种探索方法来解决这些问题,建立在熵正则化和分布初始化的想法。我们表明,这些技术可以提高性能,增加样本效率,并降低符号回归任务的解决方案的复杂性。

英文摘要:

Many machine learning strategies designed to automate mathematical tasks leverage neural networks to search large combinatorial spaces of mathematical symbols. In contrast to traditional evolutionary approaches, using a neural network at the core of the search allows learning higher-level symbolic patterns, providing an informed direction to guide the search. When no labeled data is available, such networks can still be trained using reinforcement learning. However, we demonstrate that this approach can suffer from an early commitment phenomenon and from initialization bias, both of which limit exploration. We present two exploration methods to tackle these issues, building upon ideas of entropy regularization and distribution initialization. We show that these techniques can improve the performance, increase sample efficiency, and lower the complexity of solutions for the task of symbolic regression.

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。

↑