领域之间的知识转移

如何在领域之间进行知识转移，这就是迁移学习和元学习。

课程材料

• 滑铁卢 CS885 RL PPT Multi-task RL
• Berkeley CS285 Lec 22: Meta-Learning and Transfer Learning, slides, Youtube Video

论文

斯坦福 CS 224r 论文：Multi-Task RL and Goal-Conditioned RL

• Hindsight Experience Replay. Andrychowicz et al. (2017)
• MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale Kalashnikov et al. (2021)
• Gradient Surgery for Multi-Task Learning. Yu et al. (2020)

滑铁卢 Multi-task RL 论文

• Vithayathil Varghese, N., & Mahmoud, Q. H. (2020). A survey of multi-task deep reinforcement learning. Electronics, 9(9), 1363.

斯坦福 CS 224r 论文 Meta-RL

• RL2: Fast Reinforcement Learning via Slow Reinforcement Learning. Duan et al. (2016)
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. Finn et al. (2017)
• Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices. Liu et al. (2021)

练习

• 斯坦福 CS224R DRL HW 4: Goal conditional RL， Meta RL

课本材料

N/A