cs.LG（2023-11-07）

📊 共 18 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (10) 支柱九：具身大模型 (Embodied Foundation Models) (5) 支柱一：机器人控制 (Robot Control) (3)

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

#题目一句话要点标签🔗⭐
1 Mitigating Estimation Errors by Twin TD-Regularized Actor and Critic for Deep Reinforcement Learning 提出双TD正则化的演员-评论家方法以解决深度强化学习中的估计偏差问题 reinforcement learning deep reinforcement learning DRL
2 A Novel Variational Lower Bound for Inverse Reinforcement Learning 提出变分下界方法以解决逆强化学习中的奖励函数学习问题 reinforcement learning inverse reinforcement learning
3 Reinforcement Learning Fine-tuning of Language Models is Biased Towards More Extractable Features 提出强化学习微调语言模型的新方法以提高特征提取能力 reinforcement learning large language model
4 Multi-View Causal Representation Learning with Partial Observability 提出统一框架以解决多视角因果表示学习问题 representation learning contrastive learning
5 Temporal Graph Representation Learning with Adaptive Augmentation Contrastive 提出TGAC模型以解决时间图表示学习中的噪声问题 representation learning contrastive learning
6 Context Shift Reduction for Offline Meta-Reinforcement Learning 提出上下文转移减少方法以解决离线元强化学习问题 reinforcement learning representation learning
7 SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations 提出自监督强化学习方法以应对分布外状态问题 reinforcement learning
8 Compilation of product-formula Hamiltonian simulation via reinforcement learning 提出基于强化学习的无序量子电路编译方法以优化哈密顿模拟 reinforcement learning
9 Cup Curriculum: Curriculum Learning on Model Capacity 提出杯形课程以提升模型容量的学习效果 curriculum learning
10 Learning-Based Latency-Constrained Fronthaul Compression Optimization in C-RAN 提出基于深度强化学习的前传压缩优化以满足延迟约束 reinforcement learning deep reinforcement learning DRL

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
11 Multimodal Clinical Benchmark for Emergency Care (MC-BEC): A Comprehensive Benchmark for Evaluating Foundation Models in Emergency Medicine 提出MC-BEC基准以评估急救医学中的基础模型 foundation model multimodal
12 Multitask Multimodal Prompted Training for Interactive Embodied Task Completion 提出EMMA以解决交互式具身任务完成中的语言与动作对接问题 multimodal
13 Extracting human interpretable structure-property relationships in chemistry using XAI and large language models 提出XpertAI框架以解决化学领域可解释性问题 large language model
14 Neuro-GPT: Towards A Foundation Model for EEG 提出Neuro-GPT以解决EEG数据稀缺与异质性问题 foundation model
15 Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models 证明强水印在生成模型中不可实现的理论研究 large language model

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
16 Time-Efficient Reinforcement Learning with Stochastic Stateful Policies 提出一种新方法以提高状态策略的训练效率 humanoid humanoid locomotion locomotion
17 Stable Modular Control via Contraction Theory for Reinforcement Learning 通过收缩理论实现稳定模块控制以增强强化学习的鲁棒性 manipulation reinforcement learning
18 Kernel-, mean- and noise-marginalised Gaussian processes for exoplanet transits and $H_0$ inference 提出一种全贝叶斯高斯过程以推断系外行星过境和哈勃常数 MPC

⬅️ 返回 cs.LG 首页 · 🏠 返回主页