عرض بسيط للتسجيلة

المؤلفullah, Obaid
المؤلفKhan, Habib Ullah
المؤلفHalim, Zahid
المؤلفAnwar, Sajid
المؤلفWaqas, Muhammad
تاريخ الإتاحة2024-06-24T10:20:51Z
تاريخ النشر2023-10-23
اسم المنشورACM Transactions on Sensor Networks
المعرّفhttp://dx.doi.org/10.1145/3628430
الاقتباسUllah, O., Khan, H. U., Halim, Z., Anwar, S., & Waqas, M. (2023). On Neuroevolution of Multi-Input Compositional Pattern Producing Networks: A Case of Entertainment Computing, Edge Devices, and Smart Cities. ACM Transactions on Sensor Networks
الرقم المعياري الدولي للكتاب1550-4859
معرّف المصادر الموحدhttp://hdl.handle.net/10576/56218
الملخصThis work presents a novel approach by utilizing Heterogeneous Activation Neural Networks (HA-NNs) to evolve the weights of Artificial Neural Networks (ANNs) for reinforcement learning in console and arcade computer games like Atari's Breakout and Sonic the Hedgehog. It is the first study to explore the potential of HA-NNs as potent ANNs in solving gaming-related reinforcement learning problems. Additionally, the proposed solution optimizes data transmission over networks for edge devices, marking a novel application of HA-NNs. The study achieved outstanding results, outperforming recent works in benchmark environments like CartPole-v1, Lunar Lander Continuous, and MountainCar-Continuous, with HA-NNs and ANNs evolved using the Neuroevolution of Augmenting Topologies (NEAT) algorithm. Notably, the key advancements include exceptional scores of 500 in CartPole-v1 and 98.2 in Mountain Car Continuous, demonstrating the efficacy of HA-NNs in reinforcement learning tasks. Beyond gaming, the research addresses the challenge of efficient data communication between edge devices, which has the potential to enhance performance in smart cities while reducing the load on edge devices and supporting seamless entertainment experiences with minimal commuting. This work pioneers the application of HA-NNs in reinforcement learning for computer games and introduces a novel approach for optimizing edge device communication, promising significant advancements in the fields of AI, neural networks, and smart city technologies.
اللغةen
الناشرAssociation for Computing Machinery (ACM)
الموضوعNeuroevolution
Smart City
العنوانOn Neuroevolution of Multi-Input Compositional Pattern Producing Networks: A Case of Entertainment Computing, Edge Devices, and Smart Cities
النوعArticle
ESSN1550-4867
dc.accessType Full Text


الملفات في هذه التسجيلة

Thumbnail

هذه التسجيلة تظهر في المجموعات التالية

عرض بسيط للتسجيلة