| 1 |
Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model |
提出FISOR以解决安全离线强化学习中的约束问题 |
reinforcement learning policy learning offline RL |
|
|
| 2 |
Deep Reinforcement Learning Empowered Activity-Aware Dynamic Health Monitoring Systems |
提出动态活动感知健康监测策略以优化医疗监测效率 |
reinforcement learning deep reinforcement learning DRL |
|
|
| 3 |
Episodic Reinforcement Learning with Expanded State-reward Space |
提出扩展状态-奖励空间的 episodic 强化学习以提高样本效率 |
reinforcement learning deep reinforcement learning DRL |
|
|
| 4 |
Novel Representation Learning Technique using Graphs for Performance Analytics |
提出图结构表示学习技术以提升高性能计算性能分析 |
predictive model representation learning |
|
|
| 5 |
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads |
提出Medusa框架以加速大型语言模型推理 |
distillation large language model |
|
|
| 6 |
Stochastic Dynamic Power Dispatch with High Generalization and Few-Shot Adaption via Contextual Meta Graph Reinforcement Learning |
提出上下文元图强化学习以解决多阶段随机电力调度问题 |
reinforcement learning |
|
|