BriefGPT.xyz
Jun, 2018
连续强化学习中过拟合和泛化现象的剖析
A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning
HTML
PDF
Amy Zhang, Nicolas Ballas, Joelle Pineau
TL;DR
本研究针对连续域深度强化学习方法中的过拟合问题进行了探讨，包括如何诊断及预防过拟合，增加训练多样性等，对强化学习领域的研究人员和实践者提出了实用观察。
Abstract
The risks and perils of
overfitting
in
machine learning
are well known. However most of the treatment of this, including diagnostic tools and remedies, was developed for the supervised learning case. In this work
→