部分可观察的序列学习

如果模型的是序列，那就是序列学习。有一种特别的序列是部分可观察的序列，这就是部分可观察到序列学习。

课程材料

• 滑铁卢 CS885 RL PPT RL with Sequence Modeling
• Berkeley CS285 Lec 21: RL with Sequence Models, slides, Youtube Video
• DeepMind UCL Hadovan RL 2021 Lec 11 Off-policy and multi-step
• 滑铁卢 CS885 RL PPT Partially observable RL, DRQN

论文

滑铁卢 Partially observable RL, DRQN

• Hausknecht, M., & Stone, P. Deep recurrent Q-learning for partially observable MDPs. In 2015 AAAI fall symposium series.

滑铁卢 RL with Sequence Modeling

• Esslinger, Platt & Amato (2022). Deep Transformer Q-Networks for Partially Observable Reinforcement Learning. arXiv.
• Chen et al.. (2021). Decision transformer: Reinforcement learning via sequence modeling. NeurIPS, 34, 15084-15097.
• Gu, Goel, & Ré (2022). Efficiently modeling long sequences with structured state spaces. ICLR.
• Gu, Dao, Ermon, Rudra & Ré (2020). Hippo: Recurrent memory with optimal polynomial projections. NeurIPS, 33, 1474-1487.

练习

N/A