| 1 |
Guidance Design for Escape Flight Vehicle Using Evolution Strategy Enhanced Deep Reinforcement Learning |
提出基于进化策略增强深度强化学习的逃逸飞行器制导方法 |
reinforcement learning deep reinforcement learning DRL |
|
|
| 2 |
Sub-goal Distillation: A Method to Improve Small Language Agents |
提出子目标蒸馏方法，提升小语言模型在交互式任务中的性能。 |
imitation learning distillation large language model |
|
|
| 3 |
From Generalization Analysis to Optimization Designs for State Space Models |
针对状态空间模型，提出基于泛化分析的优化设计方案，提升训练效果。 |
SSM state space model foundation model |
|
|
| 4 |
Generic Multi-modal Representation Learning for Network Traffic Analysis |
提出一种通用的多模态表征学习方法，用于网络流量分析 |
representation learning MAE |
|
|
| 5 |
Taming Equilibrium Bias in Risk-Sensitive Multi-Agent Reinforcement Learning |
提出风险平衡后悔值，解决风险敏感多智能体强化学习中的均衡偏差问题 |
reinforcement learning |
|
|