| 1 |
Integrated Sensing and Communications for Low-Altitude Economy: A Deep Reinforcement Learning Approach |
提出深度强化学习方法以优化低空经济中的集成感知与通信系统 |
reinforcement learning deep reinforcement learning DRL |
|
|
| 2 |
Hierarchical Multi-Agent DRL Based Dynamic Cluster Reconfiguration for UAV Mobility Management |
提出一种基于分层多智能体DRL的无人机动态集群重配置方法，用于优化移动性管理。 |
reinforcement learning deep reinforcement learning DRL |
|
|
| 3 |
Action Mapping for Reinforcement Learning in Continuous Environments with Constraints |
提出基于动作映射的强化学习方法，提升约束连续动作空间环境下的训练效率。 |
reinforcement learning deep reinforcement learning DRL |
|
|
| 4 |
Multi-Preference Optimization: Generalizing DPO via Set-Level Contrasts |
提出多偏好优化方法以解决直接偏好优化的局限性 |
DPO direct preference optimization |
|
|
| 5 |
Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models |
提出CAT-K闭环微调策略，提升Token化交通模型在交通仿真中的性能 |
reinforcement learning behavior cloning large language model |
✅ |
|
| 6 |
Marvel: Accelerating Safe Online Reinforcement Learning with Finetuned Offline Policy |
提出Marvel框架以加速安全在线强化学习 |
reinforcement learning policy learning |
|
|
| 7 |
Disentangled Representation Learning for Causal Inference with Instruments |
提出基于解耦表示学习的工具变量因果推断方法，解决潜在混淆变量问题。 |
representation learning |
|
|
| 8 |
BEFL: Balancing Energy Consumption in Federated Learning for Mobile Edge IoT |
提出BEFL框架以解决移动边缘物联网中的能耗不平衡问题 |
reinforcement learning imitation learning |
✅ |
|
| 9 |
ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy |
提出ELEMENT框架，通过最大熵探索实现高效的持续终身强化学习 |
reinforcement learning offline reinforcement learning |
|
|