cs.LG（2024-06-30）

📊 共 9 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (7) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning	提出基于下分位点Q学习的离线强化学习方法LEQ，提升长程任务性能。	reinforcement learning offline RL offline reinforcement learning
2	Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models	提出基于最大熵逆强化学习的扩散模型训练方法，提升生成质量并加速采样。	reinforcement learning inverse reinforcement learning
3	Benchmarks for Reinforcement Learning with Biased Offline Data and Imperfect Simulators	提出B4MRL基准测试，用于评估离线数据与不完善模拟器结合的强化学习算法	reinforcement learning offline RL offline reinforcement learning
4	Heterogeneous Graph Contrastive Learning with Spectral Augmentation	提出基于谱增强的异构图对比学习模型，提升图结构信息利用率	representation learning contrastive learning
5	Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning	提出迭代纳什策略优化(INPO)，通过无悔学习对齐LLM与通用偏好。	reinforcement learning RLHF large language model
6	Model-Free Active Exploration in Reinforcement Learning	提出一种免模型的强化学习主动探索策略，加速策略优化。	reinforcement learning
7	Enhancing Travel Decision-Making: A Contrastive Learning Approach for Personalized Review Rankings in Accommodations	提出基于对比学习的个性化评论排序方法，提升住宿选择中的用户决策。	contrastive learning

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
8	Self-consistent Deep Geometric Learning for Heterogeneous Multi-source Spatial Point Data Prediction	提出自洽深度几何学习框架，用于异构多源空间点数据预测	spatial relationship

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

#	题目	一句话要点	标签	🔗	⭐
9	Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules	Parm：通过专用调度高效训练大规模稀疏激活模型	foundation model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页