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 2104.06159cs.LGcs.AI
收藏

Muesli:结合政策优化的改进

Muesli: Combining Improvements in Policy Optimization

DeepMind(深度思维);University College London(伦敦大学学院)

Matteo Hessel, Ivo Danihelka, Fabio Viola, Arthur Guez, Simon Schmitt, Laurent Sifre, Theophane Weber, David Silver, Hado van Hasselt

摘要:

我们提出了一种新的策略更新,结合正则化的策略优化与模型学习作为辅助损失。这次更新(以下简称Muesli)与MuZero在Atari上最先进的性能相匹配。值得注意的是,Muesli在没有使用深度搜索的情况下做到了这一点:它直接与策略网络一起工作,并且具有与无模型基线相当的计算速度。Atari结果通过广泛消融以及连续控制和9x9 Go的其他结果得到补充。

英文摘要:

We propose a novel policy update that combines regularized policy optimization with model learning as an auxiliary loss. The update (henceforth Muesli) matches MuZero's state-of-the-art performance on Atari. Notably, Muesli does so without using deep search: it acts directly with a policy network and has computation speed comparable to model-free baselines. The Atari results are complemented by extensive ablations, and by additional results on continuous control and 9x9 Go.

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。

↑