| 1 |
A Survey of State Representation Learning for Deep Reinforcement Learning |
综述状态表示学习以提升深度强化学习的效率 |
reinforcement learning deep reinforcement learning representation learning |
|
|
| 2 |
Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning |
提出静态网络稀疏性以提升深度强化学习的扩展潜力 |
reinforcement learning deep reinforcement learning DRL |
|
|
| 3 |
Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity |
提出Sparse-Reg以解决离线强化学习中的小样本过拟合问题 |
reinforcement learning offline RL offline reinforcement learning |
|
|
| 4 |
TransDreamerV3: Implanting Transformer In DreamerV3 |
提出TransDreamerV3以提升复杂环境中的决策能力 |
reinforcement learning world model dreamer |
|
|
| 5 |
No Free Lunch: Rethinking Internal Feedback for LLM Reasoning |
提出内部反馈强化学习以提升大语言模型推理能力 |
reinforcement learning RLHF large language model |
|
|
| 6 |
Aha Moment Revisited: Are VLMs Truly Capable of Self Verification in Inference-time Scaling? |
探讨视觉语言模型在推理时间扩展中的自验证能力 |
reinforcement learning large language model |
|
|
| 7 |
Scalable and Reliable Multi-agent Reinforcement Learning for Traffic Assignment |
提出MARL-OD-DA以解决大规模交通分配问题 |
reinforcement learning |
|
|
| 8 |
Metapath-based Hyperbolic Contrastive Learning for Heterogeneous Graph Embedding |
提出基于元路径的双曲对比学习以解决异构图嵌入问题 |
contrastive learning |
|
|