Multi-threading parallel reinforcement learning Online publication date: Fri, 25-Oct-2019
by Qiming Fu; Yiyi Kang; Zhen Gao; Hongjie Wu; Fuyuan Hu; Jianping Chen; Shan Zhong
International Journal of Computer Applications in Technology (IJCAT), Vol. 61, No. 4, 2019
Abstract: With respect to the problem of the slow convergence of the traditional reinforcement learning algorithm in practical applications, we propose a novel multi-threading parallel reinforcement learning algorithm - MPRL. MPRL is mainly composed of two parts. One is the FCM-based reinforcement learning multi-threading partitioning method, which transforms the multi-threading partitioning problem into a clustering partition problem to obtain the optimal multi-threading partitioning solution. The other is the parallel reinforcement learning framework, which makes the parallel execution between the policy evaluation and the interaction with the environment. In the learning process, the experience replay is adopted to update the value function, which can also solve the problem of the non-convergence in the off-policy evaluation. Experimentally, the MPRL algorithm is applied to the windy grid world problem and the cart pole problem, and compared with Q-Learning, Sarsa and KCACL. The experimental results show that MPRL has a faster convergence rate and better convergence performance.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Applications in Technology (IJCAT):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com