cs.LG（2024-03-01）

📊 共 18 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) (13 🔗1) 支柱一：机器人控制 (Robot Control) (3) 支柱九：具身大模型 (Embodied Foundation Models) (2)

🔬 支柱二：RL算法与架构 (RL & Architecture) (13 篇)

#题目一句话要点标签🔗⭐
1 Snapshot Reinforcement Learning: Leveraging Prior Trajectories for Efficiency 提出SnapshotRL框架以提高深度强化学习的样本效率 reinforcement learning deep reinforcement learning DRL
2 Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey 通过对抗攻击与训练提升深度强化学习的鲁棒性 reinforcement learning deep reinforcement learning DRL
3 Robust Policy Learning via Offline Skill Diffusion 提出DuSkill框架以解决技能学习在不同领域的应用限制问题 reinforcement learning policy learning imitation learning
4 Differentially Private Knowledge Distillation via Synthetic Text Generation 提出DistilDP以解决差分隐私与模型压缩的平衡问题 distillation large language model ✅
5 Provably Robust DPO: Aligning Language Models with Noisy Feedback 提出鲁棒的DPO算法以解决噪声反馈问题 DPO direct preference optimization
6 Distributional Dataset Distillation with Subtask Decomposition 提出分布式数据集蒸馏方法以提高存储效率 distillation
7 On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Games 提出一种新型强化学习模型以解决部分可观测序列决策问题 reinforcement learning
8 Scale-free Adversarial Reinforcement Learning 提出规模无关的对抗强化学习算法解决未知奖励问题 reinforcement learning
9 Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking 提出模仿学习数据集工具包以解决数据稀缺问题 imitation learning
10 Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning 提出多种正则化技术以解决强化学习中的过估计与过拟合问题 reinforcement learning
11 Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning 提出CoMOGA以解决多目标强化学习中的梯度冲突问题 reinforcement learning
12 Efficient Reinforcement Learning for Global Decision Making in the Presence of Local Agents at Scale 提出SUBSAMPLE-Q算法以解决大规模局部智能体的全局决策问题 reinforcement learning
13 EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data 提出EfficientZero V2以解决有限数据下的强化学习样本效率问题 reinforcement learning dreamer

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
14 Autonomous Robotic Arm Manipulation for Planetary Missions using Causal Machine Learning 提出基于因果机器学习的自主机器人臂操作方法以提升行星探索效率 manipulation reinforcement learning
15 A Case for Validation Buffer in Pessimistic Actor-Critic 提出验证缓冲区以解决悲观演员-评论家中的误差累积问题 locomotion manipulation
16 VoxGenesis: Unsupervised Discovery of Latent Speaker Manifold for Speech Synthesis 提出VoxGenesis以解决无监督语音合成问题 manipulation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
17 Deciphering diffuse scattering with machine learning and the equivariant foundation model: The case of molten FeO 提出MACE-MP-0模型以解决无序材料散射数据解析问题 foundation model
18 AtP*: An efficient and scalable method for localizing LLM behaviour to components 提出AtP*以提高大语言模型行为定位的效率与可扩展性 large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页