reinforcement learning

Resolving the energy-time coupling: A deep reinforcement learning-based destroy policy for pickup-and-delivery routing

A graph isomorphism attention network and graph information embedded reinforcement learning-based dual-arm robot teleoperation and manipulation skill acquisition method

Towards Reflective AI in Digital Learning Platforms by Reinterpreting AI-Supported Language Learning

A conceptual framework for reflective AI is developed by reinterpreting four existing functions by reinterpreting four existing functions (conversational feedback, pronunciation assessment, adaptive personalization, and gamification) through Schön’s reflection-in-action and models of metacognitive regulation.

A dynamic selection framework for network-on-chip routing algorithms based on deep reinforcement learning with temporal feature extraction

Reinforcement learning-guided multi-objective particle swarm optimization with adaptive topology

ANALISIS GAYA KEPEMIMPINAN KEPALA SEKOLAH DALAM MENINGKATKAN KINERJA GURU DI SD NEGERI

Principal leadership plays a strategic role in creating a work environment that supports improvements in teaching quality and teacher instructional performance. In the context of changing demands in education, principals are expected not only to manage schools but also to implement participative and adaptive leadership...

A comprehensive review of reinforcement learning approaches in peg-in-hole insertion for robotic assembly tasks

Contributions of Positive Social Interactions to Vocal Learning and Social Cohesion

Different contributions of opioid and dopaminergic signaling to the production, reinforcement, and fine‐tuning of species‐specific songs are discussed, and ways in which reward associated with song production outside the breeding context contributes to flock cohesion are highlighted.

EdgeTwin-DRL: Real-Time Counter-UAS Detection and Response Optimization Using Edge-Assisted Digital Twins and Multi-Agent Deep Reinforcement Learning

The comparative performance of the proposed EdgeTwin-DRL architecture within the simulated environment is demonstrated and motivated to motivate further investigation of edge-assisted digital twins for counter-drone decision support.

A bibliometric analysis of research on the application of just-in-time adaptive interventions in mental health

The application of JITAIs in mental health is developing rapidly and has become a hot topic in interdisciplinary research, however, research capacity is unevenly distributed, and international collaboration needs strengthening.

Temporal coordination aware reinforcement learning for multi-agent UAV navigation in dynamic environments

T-CARE is introduced, a hybrid learning-heuristic multi-UAV coordination framework that integrates zero-shot constrained action selection with priority-aware temporal reservations and achieves 100% success, 0% collision rate, and no observed persistent starvation or deadlock.

Test-Time Weak-to-Strong Alignment: Transferring Implicit Rewards from Weak to Strong Flow Models

The method, AlignGraft, aligns a larger, frozen, never-tuned model by adding the pair's velocity difference during sampling by adding the pair's velocity difference during sampling, and preserves the large model's fidelity at a small constant sampling overhead.