| 1 |
LanGWM: Language Grounded World Model |
提出语言引导的世界模型以解决强化学习的泛化问题 |
reinforcement learning deep reinforcement learning world model |
|
|
| 2 |
Stable Online and Offline Reinforcement Learning for Antibody CDRH3 Design |
提出稳定的在线与离线强化学习方法以解决抗体CDRH3设计问题 |
reinforcement learning offline reinforcement learning |
|
|
| 3 |
TransOpt: Transformer-based Representation Learning for Optimization Problem Classification |
提出基于Transformer的优化问题分类表示学习方法 |
representation learning |
|
|
| 4 |
Maximum Entropy Model Correction in Reinforcement Learning |
提出最大熵模型修正以提升强化学习中的规划精度 |
reinforcement learning |
|
|
| 5 |
On the Adversarial Robustness of Graph Contrastive Learning Methods |
提出图对比学习的鲁棒性评估协议以应对对抗攻击 |
contrastive learning |
|
|
| 6 |
Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning |
提出偏差抗性多步离线目标条件强化学习以解决稀疏奖励问题 |
reinforcement learning |
|
|
| 7 |
The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation |
提出FairGKD以解决图神经网络公平性问题 |
distillation |
|
|