جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.

Research outputs

المخرجات البحثية

مقالات ومراجعات وأوراق مؤتمرات وفصول كتب، مفهرسة برقم DOI ومربوطة بباحثي الجامعة.

2 مُخرَج نتائج البحث عن «exploration-exploitation balance»

ورقة مؤتمروصول مغلق20251استشهاد· Semantic Scholar

Deep Reinforcement Learning-Based Multi-Robotic Agent Motion Planning

OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry (OTCON) · 1-6

The deep Q-network (DQN) technique, as a classic value-based deep reinforcement learning process, has been widely applied in fields such as multi-robotic agent motion planning. However, the DQN method faces a series of tasks, such as overestimating Q-values, complex Q-value computations, neural networks lacking historical memory proficiencies, and inefficient exploration when using ε-greedy strategies. This paper proposes a DQN-based multi-robot agent deep reinforcement learning motion planning approach to solve these problems. To accomplish their objectives without colliding with one another, agents can acquire stable and efficient motion planning techniques with the aid of this method. Initially, a Dueling-based optimization tool is suggested, which is based on the DQN approach. It simplifies and improves the calculation of Q-values by calculating state values and advantage function values, and by choosing the appropriate action based on the parameters of the presently updating Q-value network. Additionally, we provide a GRU-based memory mechanism that incorporates GRU modules to facilitate the network's temporal data acquisition and handling of agents' historical information. And lastly, we offer a noise-based exploration technique that works. By introducing parameterized noise, the exploration technique in DQN is modified, improving the examination efficiency of agents, and achieving a balance between exploration and exploitation in multi-robotic agent systems. Tests were conducted in six different simulation scenarios on the PyBullet simulation platform. Experimental results show that the proposed method enables efficient collaboration among multi-robotic agent teams, agreeing them to go where they're going without running into each other, and the methods' training is steady.

multi-robot motion planningdeep Q-networkdueling DQNexploration-exploitation balance
مقالوصول مفتوح202319استشهاد· Semantic Scholar

An efficient hybrid approach for optimization using simulated annealing and grasshopper algorithm for IoT applications

Discover Internet of Things · مجلد 3 (1)

Abstract The multi-objective grasshopper optimization algorithm (MOGOA) is a relatively new algorithm inspired by the collective behavior of grasshoppers, which aims to solve multi-objective optimization problems in IoT applications. In order to enhance its performance and improve global convergence speed, the algorithm integrates simulated annealing (SA). Simulated annealing is a metaheuristic algorithm that is commonly used to improve the search capability of optimization algorithms. In the case of MOGOA, simulated annealing is integrated by employing symmetric perturbation to control the movement of grasshoppers. This helps in effectively balancing exploration and exploitation, leading to better convergence and improved performance. The paper proposes two hybrid algorithms based on MOGOA, which utilize simulated annealing for solving multi-objective optimization problems. One of these hybrid algorithms combines chaotic maps with simulated annealing and MOGOA. The purpose of incorporating simulated annealing and chaotic maps is to address the issue of slow convergence and enhance exploitation by searching high-quality regions identified by MOGOA. Experimental evaluations were conducted on thirteen different benchmark functions to assess the performance of the proposed algorithms. The results demonstrated that the introduction of simulated annealing significantly improved the convergence of MOGOA. Specifically, the IDG (Inverse Distance Generational distance) values for benchmark functions ZDT1, ZDT2, and ZDT3 were smaller than the IDG values obtained by using MOGOA alone, indicating better performance in terms of convergence. Overall, the proposed algorithms exhibit promise in solving multi-objective optimization problems.

simulated annealinghybrid metaheuristicchaotic mapsexploration-exploitation balance