Show simple item record

Authorullah, Obaid
AuthorKhan, Habib Ullah
AuthorHalim, Zahid
AuthorAnwar, Sajid
AuthorWaqas, Muhammad
Available date2024-06-24T10:20:51Z
Publication Date2023-10-23
Publication NameACM Transactions on Sensor Networks
Identifierhttp://dx.doi.org/10.1145/3628430
CitationUllah, 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
ISSN1550-4859
URIhttp://hdl.handle.net/10576/56218
AbstractThis 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.
Languageen
PublisherAssociation for Computing Machinery (ACM)
SubjectNeuroevolution
Smart City
TitleOn Neuroevolution of Multi-Input Compositional Pattern Producing Networks: A Case of Entertainment Computing, Edge Devices, and Smart Cities
TypeArticle
ESSN1550-4867
dc.accessType Full Text


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record