cs.LG(2024-01-23)

📊 共 9 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (6) 支柱一:机器人控制 (Robot Control) (1) 支柱八:物理动画 (Physics-based Animation) (1 🔗1) 支柱三:空间感知与语义 (Perception & Semantics) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗
1 Locality Sensitive Sparse Encoding for Learning World Models Online 提出局部敏感稀疏编码以在线学习世界模型 reinforcement learning world model world models
2 Reward-Relevance-Filtered Linear Offline Reinforcement Learning 提出奖励相关性过滤的线性离线强化学习方法 reinforcement learning offline reinforcement learning
3 Stable and Safe Human-aligned Reinforcement Learning through Neural Ordinary Differential Equations 通过神经常微分方程提出安全稳定的人类对齐强化学习方法 reinforcement learning
4 Consistency Enhancement-Based Deep Multiview Clustering via Contrastive Learning 提出一致性增强的深度多视角聚类方法以解决特征表示一致性问题 contrastive learning
5 Reinforcement Learning for Graph Coloring: Understanding the Power and Limits of Non-Label Invariant Representations 提出基于强化学习的图着色方法以解决寄存器分配问题 reinforcement learning
6 Model-Free $δ$-Policy Iteration Based on Damped Newton Method for Nonlinear Continuous-Time H$\infty$ Tracking Control 提出基于阻尼牛顿法的δ-政策迭代算法以解决非线性H∞跟踪控制问题 reinforcement learning policy learning

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
7 On Building Myopic MPC Policies using Supervised Learning 提出基于监督学习的短视MPC策略以降低计算负担 MPC model predictive control

🔬 支柱八:物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗
8 Non-Neighbors Also Matter to Kriging: A New Contrastive-Prototypical Learning 提出对Kriging的新对比原型学习以解决邻居信息不足问题 spatiotemporal

🔬 支柱三:空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗
9 DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations 提出DDMI以解决隐式神经表示生成质量不足问题 neural radiance field

⬅️ 返回 cs.LG 首页 · 🏠 返回主页