Focal Interest
Focal Interest

Reinforcement learning

  1. Learnable communication graphs improve multi-agent coordination
    Study proposes learnable communication graphs for multi-agent systems, enabling dynamic information sharing that adapts to task demands and reduces computational resource consumption.
  2. AlphaLearn frames adaptive e-learning as multi-objective optimization
    AlphaLearn proposes a multi-objective evolutionary framework for adaptive e-learning pathways that integrates fairness as a core optimization criterion alongside learning effectiveness and engagement.
  3. Proactive VM consolidation cuts energy use and SLA violations
    Framework for VM consolidation combining workload prediction and physics-constrained reinforcement learning. Achieves 23.2% energy reduction and 43.5% SLA violation reduction in cloud datacenters.
  4. Hybrid deep learning improved edge-cloud task scheduling in simulation
    Deep reinforcement learning framework for adaptive task scheduling in edge-cloud computing with improved SLA compliance, reduced operational costs, and lower task rejection rates.
  5. Adaptive music generation improved emotional matching
    Emotion-Conditioned Deep Reinforcement Learning framework for adaptive music generation. Achieves 98% emotion mapping accuracy with 280ms real-time responsiveness, enabling dynamic musical.
  6. Hybrid reinforcement learning improved music teaching interaction
    Hybrid reinforcement learning architecture for adaptive music education systems combining PPO with CNN for real-time pedagogical strategy optimization and multimodal learner state classification.