| 1 |
BeTAIL: Behavior Transformer Adversarial Imitation Learning from Human Racing Gameplay |
提出BeTAIL以解决复杂环境下模仿学习的样本效率问题 |
imitation learning |
|
|
| 2 |
Generalizing Reward Modeling for Out-of-Distribution Preference Learning |
提出元学习方法以解决分布外偏好学习问题 |
reinforcement learning policy learning preference learning |
|
|
| 3 |
COPR: Continual Human Preference Learning via Optimal Policy Regularization |
提出COPR以解决人类偏好持续学习中的灾难性遗忘问题 |
reinforcement learning preference learning RLHF |
|
|
| 4 |
Contrastive Learning of Shared Spatiotemporal EEG Representations Across Individuals for Naturalistic Neuroscience |
提出CL-SSTER框架以解决自然刺激下EEG共享表示问题 |
contrastive learning spatiotemporal |
|
|
| 5 |
Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training |
提出统一离散扩散策略以解决机器人任务学习问题 |
policy learning diffusion policy multimodal |
✅ |
|
| 6 |
Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs |
提出简化REINFORCE优化方法以提升人类反馈学习效果 |
reinforcement learning PPO RLHF |
|
|
| 7 |
Practical Insights into Knowledge Distillation for Pre-Trained Models |
提出知识蒸馏优化方法以提升预训练模型在联邦学习中的表现 |
distillation |
|
|
| 8 |
Model-Based Reinforcement Learning Control of Reaction-Diffusion Problems |
提出基于模型的强化学习控制策略以解决反应扩散问题 |
reinforcement learning |
|
|
| 9 |
Representation Learning for Frequent Subgraph Mining |
提出SPMiner以解决频繁子图挖掘问题 |
representation learning |
|
|
| 10 |
Applying Reinforcement Learning to Optimize Traffic Light Cycles |
提出强化学习优化交通信号灯周期以解决交通拥堵问题 |
reinforcement learning |
|
|
| 11 |
Automated Design and Optimization of Distributed Filtering Circuits via Reinforcement Learning |
提出基于强化学习的自动化分布式滤波电路设计方法 |
reinforcement learning |
|
|
| 12 |
Quantum Circuit Optimization with AlphaTensor |
提出AlphaTensor-Quantum以解决量子电路优化问题 |
reinforcement learning deep reinforcement learning |
|
|