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 1905.03030cs.LGcs.AIstat.ML
收藏

序列策略的元学习

Meta-learning of Sequential Strategies

DeepMind
Pedro A. Ortega, Jane X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alex Pritzel, Pablo Sprechmann, Siddhan… 展开作者

Pedro A. Ortega, Jane X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alex Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin Miller, Mohammad Azar, Ian Osband, Neil Rabinowitz, András György, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado van Hasselt, Nando de Freitas, Matthew Botvinick, Shane Legg

摘要:

在这份报告中,我们回顾了基于记忆的元学习作为一种工具,用于建立样本有效的策略,从过去的经验中学习,以适应目标类中的任何任务。我们的目标是让读者了解这个工具的概念基础,以构建在广泛领域中运行的新的、可扩展的代理。为此,我们提出了基本的算法模板,用于构建接近最优的预测器和强化学习器,这些预测器和强化学习器的行为就像它们有一个概率模型,使它们能够有效地利用任务结构。此外,我们重铸基于记忆的元学习贝叶斯框架内,元学习的策略是接近最佳的,因为他们摊销贝叶斯过滤的数据,其中的适应是实现在内存动态作为一个状态机的足够的统计。本质上,基于记忆的元学习将概率顺序推理的难题转化为回归问题。

英文摘要:

In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class. Our goal is to equip the reader with the conceptual foundations of this tool for building new, scalable agents that operate on broad domains. To do so, we present basic algorithmic templates for building near-optimal predictors and reinforcement learners which behave as if they had a probabilistic model that allowed them to efficiently exploit task structure. Furthermore, we recast memory-based meta-learning within a Bayesian framework, showing that the meta-learned strategies are near-optimal because they amortize Bayes-filtered data, where the adaptation is implemented in the memory dynamics as a state-machine of sufficient statistics. Essentially, memory-based meta-learning translates the hard problem of probabilistic sequential inference into a regression problem.

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。

↑