arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.01722cs.LGcs.AIcs.NEstat.ML
收藏

全随机梯度算法及其在强化学习中的应用

Total stochastic gradient algorithms and applications in reinforcement learning

Okinawa Institute of Science and Technology Graduate University(冲绳科学技术大学院大学)

Paavo Parmas

摘要:

反向传播和导数的链式法则已经很突出;然而,全导数法则并没有得到同样的关注。在这项工作中,我们将展示如何总导数规则导致一个直观的视觉框架,用于创建图形模型上的梯度估计。特别是,以前的“策略梯度定理”很容易推导。我们基于密度估计以及似然比梯度推导出新的梯度估计量,该梯度“跳”到中间结点,而不是直接跳到目标函数。我们评估我们的方法基于模型的策略梯度算法,取得了良好的性能,并提出了证据对大众PILCO算法的成功。

英文摘要:

Backpropagation and the chain rule of derivatives have been prominent; however, the total derivative rule has not enjoyed the same amount of attention. In this work we show how the total derivative rule leads to an intuitive visual framework for creating gradient estimators on graphical models. In particular, previous "policy gradient theorems" are easily derived. We derive new gradient estimators based on density estimation, as well as a likelihood ratio gradient, which "jumps" to an intermediate node, not directly to the objective function. We evaluate our methods on model-based policy gradient algorithms, achieve good performance, and present evidence towards demystifying the success of the popular PILCO algorithm.

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。

↑