reinforcement learning

Opt DR-GNN: optimization enabled reliability prediction and hybrid deep reinforcement -graph neural network for dynamic restoration of WDM networks

The ability of an optical network to resist and recover from failures and disruptions reflects its overall effectiveness. Many practitioners and researchers are striving to realize maximum survivability of optical network systems. This paper developed a hybrid Deep Learning (DL) approach for dynamic restoration in Wave...

Thermo-electro-magneto-mechanical vibration and machine learning based multi-objective optimization of MWCNT/GNP hybrid sandwich plate with auxetic honeycomb core

The results demonstrate that the pure GNP reinforcement provides superior stiffness, whereas the balanced MWCNT:GNP ratio of 1:1 offers higher stiffness than the other hybrid reinforcement configurations and the pure CNT reinforcement exhibits the lowest stiffness.

Epistemicide with a Compute Budget: Why the Artificial Intelligence Industry's Claim to Neutrality Is a Colonial Act

Abstract Epistemicide with a Compute Budget: How Artificial Intelligence Industrializes the Colonial Erasure of Global Majority Knowledge Systems Christian ZacaTechO Ortiz Decolonial Social Scientist | Developer, Justice AI GPT | Architect, DIA Framework™ DOI: 10.5281/zenodo.22742021 This paper argues that artificial i...

Reply on RC2

Abstract. Flood risk management is increasingly challenged by climate change, rapid urbanization, and the growing complexity of hydrological systems. Reservoirs play a vital role in flood mitigation, yet traditional rule-curve operations based on historical stationarity are becoming inadequate under non-stationary and...

AI Models for Advancing Plant Tissue Culture and Bioreactors

Artificial intelligence (AI) is altering plant biotechnology by solving significant problems in tissue culture and bioreactor systems, including variability, man-power intensity, and poor reproducibility. Machine learning (ML) algorithms and artificial neural networks (ANNs) have opened the capability of simulating com...

DA-MORL: Structural-Analysis-Coupled Reinforcement Learning for Building Demolition Sequencing (code and data)

Code, trained models, and evaluation data accompanying the manuscript Building demolition sequence optimization using structural-analysis-coupled deep reinforcement learning and a CAD-to-graph representation (submitted to the Journal of Computational Design and Engineering; an earlier version was submitted under the ti...

Dynamic multi-agent deep reinforcement learning-based pricing and incentivization approach in multimodal transportation networks

In multimodal transportation systems, shared mobility services (SMSs) are promoted for their potential to enhance flexibility and reduce congestion. However, SMS demand is often concentrated in high-density areas, which can limit the effectiveness and accessibility for various commuter groups. This uneven integration c...

EH-SWADS: energy-harvesting smart weather-aware drone sink for agricultural WSNs

EH-SWADS is proposed, an energy-harvesting extension of the previously proposed weather-aware UAV-assisted WSN architecture, SWADS, designed for sustainable, long-term agricultural monitoring and explicitly incorporates the harvested-to-consumed energy balance into the learning process.

The Role of AI in Digital Circuit Design

Artificial Intelligence (AI) is increasingly being applied to digital circuit design to assist with circuit analysis, optimization, and automation. This study examines the role of AI in digital circuit design, focusing on Graph Neural Networks (GNNs), Reinforcement Learning (RL), and Generative AI. These approaches can...

Digital twin-enabled reinforcement learning for adaptive and degradation-aware control of high-temperature electrolysis

Rationality Randomization With Maximum Entropy for Robust Dynamic Obstacle Avoidance on Legged Robots

Reinforcement learning (RL) for legged robots has recently gained significant attention due to its ability to enable traversal of complex terrains and navigation in cluttered environments. However, most existing approaches focus on static or predictably moving obstacles and rely on handcrafted curricula or manual task...

A novel heterogeneous coupled neuron network and its application in mechanical fault feature enhancement

In practical engineering, fault characteristic signals are often overwhelmed by strong background noise and complex working conditions, which poses a serious challenge for timely detection and accurate identification of faults. Therefore, a novel heterogeneous coupled neuron network (HCNN) is proposed and the network u...