arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0810.5631cs.LGcs.AI
收藏

无学习率的时间差分更新

Temporal Difference Updating without a Learning Rate

IDSIA(达勒·莫尔人工智能研究所)

Marcus Hutter, Shane Legg

摘要:

我们从统计原理推导出一个时间差异学习的方程。具体来说,我们从变分原理开始,然后引导产生一个更新规则的折扣状态值估计。所得到的方程类似于用于具有资格迹线的时间差异学习的标准方程,所谓的TD(lambda),然而它缺少指定学习率的参数alpha。在这个自由参数的地方,现在有一个特定于每个状态转换的学习率的方程。我们通过实验测试了这个新的学习规则对TD(lambda),并发现它提供了优越的性能在各种设置。最后,我们对如何将新的时间差分算法扩展到强化学习进行了初步的研究。为此,我们将更新方程与Watkins的Q(lambda)和Sarsa(lambda)结合起来,发现它在没有学习率参数的情况下再次提供了优异的性能。

英文摘要:

We derive an equation for temporal difference learning from statistical principles. Specifically, we start with the variational principle and then bootstrap to produce an updating rule for discounted state value estimates. The resulting equation is similar to the standard equation for temporal difference learning with eligibility traces, so called TD(lambda), however it lacks the parameter alpha that specifies the learning rate. In the place of this free parameter there is now an equation for the learning rate that is specific to each state transition. We experimentally test this new learning rule against TD(lambda) and find that it offers superior performance in various settings. Finally, we make some preliminary investigations into how to extend our new temporal difference algorithm to reinforcement learning. To do this we combine our update equation with both Watkins' Q(lambda) and Sarsa(lambda) and find that it again offers superior performance without a learning rate parameter.

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。

↑