reinforcement learning

Vulnerability-aware reinforcement learning scheduling of AI data centers under typhoon-induced thermal coupling

The rapid growth of AI data-center loads, amplified by typhoon-induced thermal coupling between workloads and cooling systems, poses new challenges to transmission grid vulnerability assessment and scheduling. This paper develops a vulnerability-aware reinforcement-learning (RL) scheduling framework that integrates a m...

PANES: Policy-guided Asymmetric Nash Equilibrium Search

Trick-taking card games with mandatory bidding confront reinforcement learning agents with a distinctive two-phase problem: each player must commit to a numeric bid before any cards are played, and whether that bid turns out to be correct hinges on adversarial interactions unfolding over many subsequent tricks. Judgeme...

A deep learning and blockchain enabled adaptive routing framework for secure Vehicular Ad Hoc Networks

Vehicular Ad hoc Networks (VANETs) are one of the most important enablers of Intelligent Transportation Systems (ITSs), however, their dynamic topologies and susceptibility to malicious activities provide a serious challenge to the routing efficiency and security. To address these challenges, this paper introduces a ne...

Reinforcement Learning in Serious Games: an Exploratory Analysis

Step-Level Gradient Masking for GRPO: Selective Optimization of Reasoning Trajectories

Group Relative Policy Optimization (GRPO) has recently emerged as an effective algorithm for Reinforcement Learning from Verifiable Rewards (RLVR), allowing for improvements in logical reasoning, more specifically in mathematical reasoning in large language models (LLMs) without supervised reasoning traces. It does, ho...

Reinforcement Learning: Emerging Trends and Future Research Directions

Active suspension preview control via deep reinforcement learning with hybrid synchronizing policy and hierarchical road perception

The rapid advancement of vehicle electronic control systems has provided favorable support for enhancing the dynamic response and control performance of suspension systems. Conventional control strategies based on suspension state feedback are limited in their active adjustment capability due to the lack of utilization...

A context-aware multimodal multi-agent deep reinforcement learning framework for autonomous personalized education

This paper introduces the Context-Aware Multi-Agent Deep Reinforcement Learning (CA-MA-DRL) framework for personalised digital education, shifting from passive analytics to autonomous decision-making agents. The framework integrates Multimodal Learning Analytics with advanced coordination mechanisms, fusing heterogeneo...

Toward zero-shot generalization of deep reinforcement learning for hybrid energy system dispatch

Motivational Strategies Used by Filipino English as a Foreign Language Teachers in Taiwanese Elementary

This descriptive qualitative study explored the motivational strategies used by Filipino English as a Foreign Language (EFL) teachers in Taiwanese public elementary schools. Situated within Taiwan’s Bilingual 2030 policy context, the inquiry examined the strategies teachers used to engage young learners, the perceived...

Reinforcement learning–coupled neural ode modelling reveals ferroptotic resolution failure as a shared dynamical axis linking periodontitis and coronary atherogenesis

The molecular axis underlying the epidemiologically established association between periodontitis and coronary heart disease (CHD) remains undefined at mechanistic, systems-level resolution. Classical comparative transcriptomics captures correlational gene lists but cannot reconstruct directional disease-state dynamics...

Emergency Evacuation in Classrooms: A Review

Classroom evacuation is constrained by relatively fixed occupant positions, dense desk-and-chair arrangements, restricted aisles, and limited exits, and is jointly influenced by occupant behavior, spatial conditions, and emergency scenarios. This review proposes a four-stage framework comprising scenario and data, expe...