| 1 |
Blockchain-based Crowdsourced Deep Reinforcement Learning as a Service |
提出基于区块链的众包深度强化学习即服务框架，降低DRL应用门槛。 |
reinforcement learning deep reinforcement learning DRL |
|
|
| 2 |
Online Preference Alignment for Language Models via Count-based Exploration |
提出COPO算法，通过计数探索实现语言模型在线偏好对齐 |
reinforcement learning RLHF direct preference optimization |
|
|
| 3 |
Deep Reinforcement Learning with Hybrid Intrinsic Reward Model |
提出HIRE框架，通过混合内在奖励提升强化学习探索效率与技能学习 |
reinforcement learning deep reinforcement learning reward shaping |
|
|
| 4 |
Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors |
SWIRL：一种结合时变奖励与历史依赖的逆强化学习方法，用于刻画动物行为 |
reinforcement learning inverse reinforcement learning |
|
|
| 5 |
Adaptive Data Exploitation in Deep Reinforcement Learning |
提出ADEPT框架，通过自适应数据利用提升深度强化学习的数据效率和泛化性。 |
reinforcement learning deep reinforcement learning |
✅ |
|
| 6 |
To Measure or Not: A Cost-Sensitive, Selective Measuring Environment for Agricultural Management Decisions with Reinforcement Learning |
提出基于强化学习的成本敏感型农业管理决策环境，优化作物测量与施肥 |
reinforcement learning PPO |
|
|
| 7 |
PPO-Based Vehicle Control for Ramp Merging Scheme Assisted by Enhanced C-V2X |
提出基于PPO和增强C-V2X的匝道汇入车辆控制方案，提升安全性与效率。 |
reinforcement learning PPO |
|
|
| 8 |
Exploring the Technology Landscape through Topic Modeling, Expert Involvement, and Reinforcement Learning |
提出结合主题建模与强化学习的方法以应对技术变革挑战 |
reinforcement learning |
|
|
| 9 |
Enhancing Multi-Attribute Fairness in Healthcare Predictive Modeling |
提出一种多属性公平性优化方法，提升医疗AI预测模型的公平性 |
predictive model |
|
|
| 10 |
Attention-Driven Hierarchical Reinforcement Learning with Particle Filtering for Source Localization in Dynamic Fields |
提出基于注意力机制的分层强化学习框架，解决动态场中源定位问题 |
reinforcement learning |
|
|
| 11 |
A Probabilistic Model for Non-Contrastive Learning |
提出基于概率模型的非对比学习框架，揭示其与PCA和非对比损失的联系 |
contrastive learning |
|
|
| 12 |
An Offline Multi-Agent Reinforcement Learning Framework for Radio Resource Management |
提出离线多智能体强化学习框架，用于无线资源管理，提升用户速率。 |
reinforcement learning |
|
|
| 13 |
Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science |
提出对比语言-结构预训练(CLaSP)，用于材料科学中基于文本的晶体结构检索。 |
contrastive learning |
|
|
| 14 |
HierPromptLM: A Pure PLM-based Framework for Representation Learning on Heterogeneous Text-rich Networks |
提出HierPromptLM，一个纯PLM框架，用于异构富文本网络表示学习。 |
representation learning |
|
|
| 15 |
Graph Representation Learning with Diffusion Generative Models |
提出基于扩散生成模型的图表示学习方法，有效提取图结构数据的嵌入。 |
representation learning |
✅ |
|
| 16 |
On Generalization and Distributional Update for Mimicking Observations with Adequate Exploration |
提出MODULE算法，通过分布更新学习模仿观测，解决模仿学习中的探索不足和不稳定性问题 |
reinforcement learning SAC |
|
|
| 17 |
GRAMA: Adaptive Graph Autoregressive Moving Average Models |
提出GRAMA：一种自适应图自回归移动平均模型，用于增强图神经网络的远程依赖建模能力。 |
SSM state space model |
|
|
| 18 |
Knowledge-Driven Federated Graph Learning on Model Heterogeneity |
提出FedGKC框架，解决联邦图学习中模型异构场景下的知识迁移与聚合问题。 |
representation learning distillation |
|
|