cs.LG（2025-01-11）
📊 共 5 篇论文
🎯 兴趣领域导航
支柱二：RL算法与架构 (RL & Architecture) (3)
支柱一：机器人控制 (Robot Control) (1)
支柱九：具身大模型 (Embodied Foundation Models) (1)
🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Task Delay and Energy Consumption Minimization for Low-altitude MEC via Evolutionary Multi-objective Deep Reinforcement Learning | 提出基于演化多目标深度强化学习的低空MEC任务延迟与能耗最小化方法 | reinforcement learning deep reinforcement learning DRL | ||
| 2 | Influencing Humans to Conform to Preference Models for RLHF | 通过影响人类偏好表达，使之更符合RLHF的偏好模型假设 | reinforcement learning RLHF | ||
| 3 | Hierarchical Reinforcement Learning for Optimal Agent Grouping in Cooperative Systems | 提出一种层级强化学习方法，解决合作多智能体系统中的最优分组问题。 | reinforcement learning |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Reinforcement Learning for Enhancing Sensing Estimation in Bistatic ISAC Systems with UAV Swarms | 提出基于多智能体强化学习的无人机群ISAC系统感知增强方法 | trajectory optimization reinforcement learning |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping | 提出Ladder Residual架构，通过通信重叠加速大模型并行推理。 | large language model |