cs.LG（2023-10-31）

📊 共 19 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) (14 🔗1) 支柱八：物理动画 (Physics-based Animation) (2) 支柱一：机器人控制 (Robot Control) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (14 篇)

#题目一句话要点标签🔗⭐
1 Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning 提出LaMo框架以解决离线强化学习中的数据稀缺问题 reinforcement learning offline RL offline reinforcement learning
2 Closed Drafting as a Case Study for First-Principle Interpretability, Memory, and Generalizability in Deep Reinforcement Learning 提出基于第一原理的深度强化学习可解释性研究方法 reinforcement learning deep reinforcement learning DRL
3 The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback 提出解决人类反馈强化学习中的目标不匹配问题 reinforcement learning RLHF large language model
4 Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents 提出重置深度集成代理以解决深度强化学习中的样本效率和安全性问题 reinforcement learning deep reinforcement learning
5 A Tractable Inference Perspective of Offline RL 提出Trifle以解决离线强化学习中的可处理性问题 reinforcement learning offline RL offline reinforcement learning
6 Offline RL with Observation Histories: Analyzing and Improving Sample Complexity 提出观察历史的离线强化学习方法以改善样本复杂度 reinforcement learning offline RL offline reinforcement learning
7 Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback 提出一种基于人类反馈的自主机器人强化学习方法 reinforcement learning policy learning ✅
8 Dropout Strategy in Reinforcement Learning: Limiting the Surrogate Objective Variance in Policy Optimization Methods 提出Dropout策略以解决强化学习中的目标方差问题 reinforcement learning PPO
9 Towards Instance-Optimality in Online PAC Reinforcement Learning 提出实例依赖的下界以优化在线PAC强化学习 reinforcement learning
10 LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B 提出LoRA微调方法以有效解除Llama 2-Chat的安全训练 reinforcement learning large language model
11 Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement Learning 提出Amoeba以解决机器学习支持的网络审查问题 reinforcement learning
12 Network Contention-Aware Cluster Scheduling with Reinforcement Learning 提出基于强化学习的网络争用感知集群调度方法 reinforcement learning
13 Generative Learning of Continuous Data by Tensor Networks 提出连续数据生成模型以解决现有方法局限性 world model world models
14 Contrastive Difference Predictive Coding 提出时间差对比预测编码以提高强化学习效率 reinforcement learning representation learning

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
15 Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data 提出Neuroformer以解决系统神经科学中的多模态数据分析问题 spatiotemporal multimodal
16 Fast, accurate, and interpretable decoding of electrocorticographic signals using dynamic mode decomposition 提出空间动态模式特征以解决神经解码的实时性与可解释性问题 spatiotemporal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
17 Coalitional Manipulations and Immunity of the Shapley Value 提出新基础以解决沙普利值的煤团操控问题 manipulation

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

#题目一句话要点标签🔗⭐
18 AutoMixer for Improved Multivariate Time-Series Forecasting on Business and IT Observability Data 提出AutoMixer以解决Biz-KPI预测中的噪声干扰问题 foundation model

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

#题目一句话要点标签🔗⭐
19 Deep Compressed Learning for 3D Seismic Inversion 提出深度压缩学习以解决3D地震反演问题 3D reconstruction

⬅️ 返回 cs.LG 首页 · 🏠 返回主页