cs.LG（2023-11-09）

📊 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) (5 🔗1) 支柱一：机器人控制 (Robot Control) (3) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations	通过RL在想象对话中实现零样本目标导向对话	reinforcement learning offline reinforcement learning RLHF
2	Hard-Negative Sampling for Contrastive Learning: Optimal Representation Geometry and Neural- vs Dimensional-Collapse	提出硬负样本采样以优化对比学习中的表示几何	representation learning contrastive learning	✅
3	Anytime-Constrained Reinforcement Learning	提出带有随时约束的强化学习方法以解决预算限制问题	reinforcement learning
4	Fair Wasserstein Coresets	提出公平Wasserstein核心集以解决数据偏见问题	distillation large language model
5	Diffusion Based Causal Representation Learning	提出基于扩散的因果表示学习以解决因果推理挑战	representation learning

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
6	Accelerating Exploration with Unlabeled Prior Data	提出利用无标签先验数据加速稀疏奖励任务探索	manipulation reinforcement learning
7	LLM Augmented Hierarchical Agents	提出层次化代理以解决长时间任务的强化学习问题	manipulation reinforcement learning
8	Improving Computational Efficiency for Powered Descent Guidance via Transformer-based Tight Constraint Prediction	提出基于Transformer的动力下降引导算法以提高计算效率	trajectory optimization

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
9	Efficient Parallelization Layouts for Large-Scale Distributed Model Training	提出高效并行布局以优化大规模分布式模型训练	large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页