A Reward Optimization Method Based on Action Subrewards in Hierarchical Reinforcement Learning

المؤلفون المشاركون

Liu, Quan
Fu, Yuchen
Ling, Xionghong
Cui, Zhiming

المصدر

The Scientific World Journal

العدد

المجلد 2014، العدد 2014 (31 ديسمبر/كانون الأول 2014)، ص ص. 1-6، 6ص.

الناشر

Hindawi Publishing Corporation

تاريخ النشر

2014-01-28

دولة النشر

مصر

عدد الصفحات

6

التخصصات الرئيسية

الطب البشري
تكنولوجيا المعلومات وعلم الحاسوب

الملخص EN

Reinforcement learning (RL) is one kind of interactive learning methods.

Its main characteristics are “trial and error” and “related reward.” A hierarchical reinforcement learning method based on action subrewards is proposed to solve the problem of “curse of dimensionality,” which means that the states space will grow exponentially in the number of features and low convergence speed.

The method can reduce state spaces greatly and choose actions with favorable purpose and efficiency so as to optimize reward function and enhance convergence speed.

Apply it to the online learning in Tetris game, and the experiment result shows that the convergence speed of this algorithm can be enhanced evidently based on the new method which combines hierarchical reinforcement learning algorithm and action subrewards.

The “curse of dimensionality” problem is also solved to a certain extent with hierarchical method.

All the performance with different parameters is compared and analyzed as well.

نمط استشهاد جمعية علماء النفس الأمريكية (APA)

Fu, Yuchen& Liu, Quan& Ling, Xionghong& Cui, Zhiming. 2014. A Reward Optimization Method Based on Action Subrewards in Hierarchical Reinforcement Learning. The Scientific World Journal،Vol. 2014, no. 2014, pp.1-6.
https://search.emarefa.net/detail/BIM-1048351

نمط استشهاد الجمعية الأمريكية للغات الحديثة (MLA)

Fu, Yuchen…[et al.]. A Reward Optimization Method Based on Action Subrewards in Hierarchical Reinforcement Learning. The Scientific World Journal No. 2014 (2014), pp.1-6.
https://search.emarefa.net/detail/BIM-1048351

نمط استشهاد الجمعية الطبية الأمريكية (AMA)

Fu, Yuchen& Liu, Quan& Ling, Xionghong& Cui, Zhiming. A Reward Optimization Method Based on Action Subrewards in Hierarchical Reinforcement Learning. The Scientific World Journal. 2014. Vol. 2014, no. 2014, pp.1-6.
https://search.emarefa.net/detail/BIM-1048351

نوع البيانات

مقالات

لغة النص

الإنجليزية

الملاحظات

Includes bibliographical references

رقم السجل

BIM-1048351