引用本概念的论文(3)
- 扩散引导的不确定性感知延迟策略优化 Diffusion-Guided Uncertainty-Aware Delayed Policy Optimization arXiv 2607.05064
- 用于高效离线强化学习的捷径轨迹规划 Shortcut Trajectory Planning for Efficient Offline Reinforcement Learning arXiv 2607.09336
- 通过生成式随机化与跨变体自监督学习打破虚假相关性 Breaking Spurious Correlations via Generative Randomization and Cross-Variant Self-Supervised Learning arXiv 2607.05850