BriefGPT.xyz
Jan, 2019
深度神经线性赌博机: 通过似然匹配克服灾难性遗忘
Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching
HTML
PDF
Tom Zahavy, Shie Mannor
TL;DR
研究采用神经线性策略模型解决高维度副信息序列决策问题,并设计了可用于线性上下文策略的高效探测机制,提出具有限内存神经线性策略防止该现象的新方法。通过在回归、分类和情感分析等各种真实世界数据集上评估我们的方法,我们得到了鲁棒性和优越性能。
Abstract
We study the
neural-linear bandit model
for solving
sequential decision-making
problems with high dimensional side information. Neural-linear bandits leverage the representation power of
→