arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0803.3539cs.NEcs.AI
收藏

基于价值服从的强化学习

Reinforcement Learning by Value Gradients

Gatsby Computational Neuroscience Unit(盖茨比计算神经科学单元)

Michael Fairbank

摘要:

值梯度的概念是在强化学习的背景下引入和发展的。它表明,通过学习的值梯度探索或随机行为不再需要找到局部最优轨迹。这是使用值梯度的主要动机,并且有人认为学习值梯度是用于控制问题的任何值函数学习算法的实际目标。也有人认为,学习值梯度是显着更有效的学习值,这一论点是支持在实验中的效率增益的几个数量级,在几个问题领域。一旦将值梯度引入学习,几种分析就成为可能。例如,证明了值梯度学习算法和策略梯度学习算法之间令人惊讶的等价性,并且这为使用具有一般函数逼近器的价值函数的控制问题提供了鲁棒的收敛性证明。

英文摘要:

The concept of the value-gradient is introduced and developed in the context of reinforcement learning. It is shown that by learning the value-gradients exploration or stochastic behaviour is no longer needed to find locally optimal trajectories. This is the main motivation for using value-gradients, and it is argued that learning value-gradients is the actual objective of any value-function learning algorithm for control problems. It is also argued that learning value-gradients is significantly more efficient than learning just the values, and this argument is supported in experiments by efficiency gains of several orders of magnitude, in several problem domains. Once value-gradients are introduced into learning, several analyses become possible. For example, a surprising equivalence between a value-gradient learning algorithm and a policy-gradient learning algorithm is proven, and this provides a robust convergence proof for control problems using a value function with a general function approximator.

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。

↑