cs.LG（2023-10-15）

📊 共 14 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (10 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
1 Deep Reinforcement Learning with Explicit Context Representation 提出Iota显式上下文表示框架以解决强化学习中的上下文学习问题 reinforcement learning deep reinforcement learning affordance
2 Alpha Elimination: Using Deep Reinforcement Learning to Reduce Fill-In during Sparse Matrix Decomposition 提出Alpha Elimination以减少稀疏矩阵分解中的填充问题 reinforcement learning deep reinforcement learning ✅
3 Specialized Deep Residual Policy Safe Reinforcement Learning-Based Controller for Complex and Continuous State-Action Spaces 提出专门的深度残差策略安全强化学习控制器以解决复杂状态-动作空间问题 reinforcement learning deep reinforcement learning policy learning
4 AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents 提出AMAGO以解决长序列强化学习中的可扩展性问题 reinforcement learning policy learning
5 Farzi Data: Autoregressive Data Distillation 提出Farzi以优化自回归任务的数据蒸馏 distillation
6 Federated Reinforcement Learning for Resource Allocation in V2X Networks 提出联邦强化学习以优化V2X网络中的资源分配问题 reinforcement learning
7 Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization 提出互信息正则化方法以解决多智能体强化学习的鲁棒性问题 reinforcement learning
8 MAGIC: Detecting Advanced Persistent Threats via Masked Graph Representation Learning 提出MAGIC以解决APT检测中的多重挑战 representation learning
9 DropMix: Better Graph Contrastive Learning with Harder Negative Samples 提出DropMix以解决图对比学习中的负样本生成问题 contrastive learning ✅
10 Enhancing Column Generation by Reinforcement Learning-Based Hyper-Heuristic for Vehicle Routing and Scheduling Problems 提出基于强化学习的超启发式方法以增强列生成算法在车辆调度中的应用 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
11 Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs 提出LLM4NG以解决文本属性图的少样本学习问题 large language model
12 Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models 提出Chameleon以高效支持检索增强语言模型 large language model
13 UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting 提出UniTime以解决跨领域时间序列预测问题 zero-shot transfer

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 ACES: Generating Diverse Programming Puzzles with with Autotelic Generative Models 提出ACES以自动生成多样化编程难题 manipulation large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页