reinforcement learning

Runtime Attribution in PPO with Predictive Action Projection: An Independent-Run Fixed-to-Transfer Audit

This paper examines how to evaluate a reinforcement-learning controller whose proposed actions are modified by an online projector. Using PPO in simulated constrained navigation, it focuses on distinguishing the performance of the policy evaluated without projection from that of the complete controller operating with p...

Reinforcement Learning-Based Compliant Locomotion for Sensorless Humanoids in Physical Human-Robot Interaction with Sim-to-Real Force Dispersion Compensation

Contact Force Estimation-Guided Reinforcement Learning Framework for Compliant Humanoid Bipedal Walking

Federated reinforcement learning-based cooperative operation of community microgrids with electric vehicle charging and swapping stations using asymmetric Nash bargaining

Cost-effective tariff-aware HVAC coordination in Saudi residential buildings using physics-informed deep reinforcement learning

Abstract When multiple On/Off split air-conditioning units in Saudi residential buildings activate simultaneously, the resulting peak demand spike stresses the electrical grid and inflates monthly bills under the kingdom’s two-tier tariff (0.18 SAR/kWh $$\leq$$ 6,000 kWh; 0.30 SAR/kWh above). This paper proposes a Phys...

Deep Reinforcement Learning for Security-Aware Task Offloading in IoT Edge Computing: A Systematic Survey of Frameworks, Challenges, and Future Directions

Background: IoT devices deployed in hospitals, factories, vehicles, and homes are largely unable to defend themselves. Limited compute and power budgets make running a local intrusion detector impractical, even as the traffic these devices generate grows increasingly attractive to attackers. DRL offers a practical alte...

A comprehensive survey of Edge-Fog-Cloud-IoT architectures: Intelligence, Security, and Sustainability

The rapid expansion of IoT devices has resulted in a paradigm shift from centralized cloud computing models to highly distributed computing continua that incorporate IoT devices, edge gateways, fog nodes, regional cloudlets, and hyperscale cloud data centers. In this survey, we provide an overview of Edge-Fog-Cloud-IoT...

Calibrated Confidence Expression for Radiology Report Generation

ConRad (Confidence Calibration for Radiology Reports), a reinforcement learning framework for fine-tuning medical LVLMs to produce calibrated verbalized confidence estimates alongside radiology reports, is introduced and substantially improves calibration and outperforms competing methods.

Feedback-driven rule induction and retrieval-augmented bias mitigation for large language models

Large Language Models (LLMs) are becoming widely adopted for reasoning and decision-support tasks, yet they can inherit and reproduce gender-related biases present in their training data. Most existing bias-mitigation strategies depend on fine-tuning, reinforcement learning, prompt engineering, or interventions dur...

Efficient Communication Management in Diffractive Optics IoT Networks for Intelligent Video Transmission

DOECOM-VID is suggested, a novel architecture that employs diffractive optical elements (DOEs) for interference-free parallel data distribution, phase-front shaping, and multi-channel optical beamforming for real-time video transmission in dynamic, intelligent video-centric Internet of Things networks.

Product and Distribution Strategies for Educational Services from the Perspective of Islamic Education Management in the Era of Digital Transformation: A Field Study at MIN 1 West Jakarta

Digitalization in Islamic education is becoming increasingly relevant for developing effective product and distribution strategies to address the challenges of the digital transformation era. This study aims to analyze the implementation of product and distribution strategies for educational services within the framewo...

Reinforcement learning-driven vehicular content caching

In-network caching can shorten the distances between consumers and contents. Therefore, we leverage in-network caching to enable vehicles to rapidly access vehicular contents such as road conditions, thereby giving vehicles sufficient time to correctly handle potential road hazards ahead. We propose a reinforcement lea...