دسته بندی:
محاسبات کوانتومی - Quantum-Computing
سال انتشار:
2022
عنوان انگلیسی مقاله:
Deep Reinforcement Learning With Quantum-Inspired Experience Replay
ترجمه فارسی عنوان مقاله:
یادگیری تقویتی عمیق با تکرار تجربه کوانتومی
منبع:
ieee - ieee Transactions on Cybernetics;2022;52;9;10:1109/TCYB:2021:3053414
نویسنده:
Qing Wei; Hailan Ma; Chunlin Chen; Daoyi Dong
چکیده انگلیسی:
In this article, a novel training paradigm inspired
by quantum computation is proposed for deep reinforcement
learning (DRL) with experience replay. In contrast to the traditional experience replay mechanism in DRL, the proposed DRL
with quantum-inspired experience replay (DRL-QER) adaptively
chooses experiences from the replay buffer according to the
complexity and the replayed times of each experience (also
called transition), to achieve a balance between exploration and
exploitation. In DRL-QER, transitions are first formulated in
quantum representations and then the preparation operation
and depreciation operation are performed on the transitions.
In this process, the preparation operation reflects the relationship between the temporal-difference errors (TD-errors) and the
importance of the experiences, while the depreciation operation is
taken into account to ensure the diversity of the transitions. The
experimental results on Atari 2600 games show that DRL-QER
outperforms state-of-the-art algorithms, such as DRL-PER and
DCRL on most of these games with improved training efficiency
and is also applicable to such memory-based DRL approaches
as double network and dueling network.
Index Terms: Deep reinforcement learning (DRL) | quantum computation | quantum-inspired experience replay (QER) | quantum reinforcement learning.
قیمت: رایگان
توضیحات اضافی:
تعداد نظرات : 0