引用本概念的论文(2)
- ExToken:利用离散行为先验实现视觉-语言-动作强化学习中的高效探索 ExToken: Leveraging Discrete Behavioral Priors for Efficient Exploration in Vision-Language-Action Reinforcement Learning arXiv 2607.12931
- 以少学多:基于事后回溯的强化学习 Learning More from Less: Reinforcement Learning from Hindsight arXiv 2607.09042