BriefGPT.xyz
Jul, 2020
预测信息加速强化学习
Predictive Information Accelerates Learning in RL
HTML
PDF
Kuang-Huei Lee, Ian Fischer, Anthony Liu, Yijie Guo, Honglak Lee...
TL;DR
本文通过使用有监督训练的压缩表示学习了强化学习环境动态的预测信息，通过提高样本效率使得 Soft Actor-Critic 代理人可以大幅度地改善在连续控制任务中的表现。
Abstract
The
predictive information
is the mutual information between the past and the future, I(X_past; X_future). We hypothesize that capturing the
predictive information
is useful in RL, since the ability to model what
→