简体繁体 English

强化学习方法，将连续映射到连续映射

[英]Reinforcement learning methodes that map continuous to continuous

原文 2012-07-27 23:47:53 2 1 python/ machine-learning/ reinforcement-learning/ economics

I am building a model where firms have to set prices and make production decisions. 我正在建立一个模型，公司必须设定价格并做出生产决策。 Prices are continuous and so are the decision variables. 价格是连续的，决策变量也是如此。 (inventory, last sales, prices...). （库存，上次销售，价格......）。

What reinforcement learning method can I use that maps continuous to continuous ? 我可以使用哪种强化学习方法将图连续到连续？ Which python packages are there? 有哪些python包？ If there are no python packages, I could write a wrapper. 如果没有python包，我可以编写一个包装器。

1 个解决方案

PyBrain machine learning library is what you're looking for. PyBrain机器学习库是您正在寻找的。 It is quite complex implementation of neural networks, but when you understand it you will get a really powerful tool. 这是神经网络的相当复杂的实现，但是当你理解它时，你将获得一个非常强大的工具。

PyBrain is a python library for neural network modeling. PyBrain是一个用于神经网络建模的python库。 Overview of the PyBrain should get you a basic idea: at each timestamp you provides neural network with a set of continuous values and take out another set of continuous values. PyBrain概述应该为您提供一个基本想法：在每个时间戳，您为神经网络提供一组连续值，并取出另一组连续值。 But more important is that you can evaluate the output and train your neural network. 但更重要的是，您可以评估输出并训练您的神经网络。

All these steps - including network training - are already implemented in PyBrain. 所有这些步骤 - 包括网络培训 - 已经在PyBrain中实现。