cs.LG（2023-12-07）

📊 共 16 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 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱一：机器人控制 (Robot Control) (1 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1)

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

#题目一句话要点标签🔗⭐
1 MICRO: Model-Based Offline Reinforcement Learning with a Conservative Bellman Operator 提出基于保守贝尔曼算子的模型离线强化学习算法MICRO，提升策略鲁棒性。 reinforcement learning offline RL offline reinforcement learning
2 Efficient Parallel Reinforcement Learning Framework using the Reactor Model 提出基于Reactor模型的并行强化学习框架，提升训练与推理效率。 reinforcement learning
3 Relational Deep Learning: Graph Representation Learning on Relational Databases 提出关系深度学习（RDL），直接在关系数据库上进行图表示学习，无需人工特征工程。 representation learning
4 Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation 提出UCRL-WVTR算法以解决长规划时间问题 reinforcement learning
5 Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization 提出Q-Uncertainty Soft Actor-Critic算法，用于风险感知的模型强化学习策略优化 reinforcement learning SAC offline RL
6 A Scalable Network-Aware Multi-Agent Reinforcement Learning Framework for Decentralized Inverter-based Voltage Control 提出可扩展的网络感知多智能体强化学习框架，解决分布式逆变器电压分散控制问题 reinforcement learning
7 Urban Region Representation Learning with Attentive Fusion 提出HAFusion模型，通过注意力融合学习城市区域表征，提升城市规划应用效果。 representation learning
8 CODEX: A Cluster-Based Method for Explainable Reinforcement Learning 提出基于聚类的可解释强化学习方法CODEX，提升高风险场景应用中的用户信任。 reinforcement learning
9 Improving Communication Efficiency of Federated Distillation via Accumulating Local Updates 提出ALU：通过累积本地更新提升联邦蒸馏的通信效率 distillation
10 TimeDRL: Disentangled Representation Learning for Multivariate Time-Series TimeDRL：提出解耦表征学习框架，提升多元时间序列预测与分类性能。 representation learning ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
11 LLM4TDD: Best Practices for Test Driven Development Using Large Language Models LLM4TDD：探索利用大型语言模型进行测试驱动开发的最佳实践 large language model
12 Using Large Language Models for Hyperparameter Optimization 利用大型语言模型进行超参数优化，提升小样本学习性能 large language model
13 Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models CyberSecEval：用于评估语言模型安全编码能力的综合基准测试 large language model
14 Testing LLM performance on the Physics GRE: some observations 评估大型语言模型Bard在物理GRE考试中的表现与局限性 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
15 Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations 提出因果感知度量学习方法，提升多智能体交互表示的Sim-to-Real迁移能力 sim-to-real sim2real ✅

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
16 NeuJeans: Private Neural Network Inference with Joint Optimization of Convolution and FHE Bootstrapping NeuJeans：通过卷积与FHE自举联合优化实现私有神经网络推理 OMOMO

⬅️ 返回 cs.LG 首页 · 🏠 返回主页