arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1806.07692cs.LGstat.ML
收藏

基于增强神经网络的强化学习

Reinforcement Learning using Augmented Neural Networks

University of Kent(肯特大学)

Jack Shannon, Marek Grzes

摘要:

神经网络允许Q学习强化学习代理,如深度Q网络(DQN),以近似从状态空间到价值函数的复杂映射。然而,当与其他函数逼近器(例如瓦片编码或其泛化、径向基函数(RBF))相比时,这也带来缺点,因为它们由于神经网络中存在的全局化更新的副作用而引入不稳定性。这种不稳定性甚至不会在没有任何隐藏层的神经网络中消失。在本文中,我们表明,简单的修改结构的神经网络可以提高稳定性的DQN学习时,多层感知器用于函数逼近。

英文摘要:

Neural networks allow Q-learning reinforcement learning agents such as deep Q-networks (DQN) to approximate complex mappings from state spaces to value functions. However, this also brings drawbacks when compared to other function approximators such as tile coding or their generalisations, radial basis functions (RBF) because they introduce instability due to the side effect of globalised updates present in neural networks. This instability does not even vanish in neural networks that do not have any hidden layers. In this paper, we show that simple modifications to the structure of the neural network can improve stability of DQN learning when a multi-layer perceptron is used for function approximation.

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。

↑