【刷b站】

Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning
https://arxiv.org/abs/1812.03509
对话生成：模仿学习到逆强化学习
https://www.bilibili.com/video/BV1Wa4y1Y7kW

Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
https://arxiv.org/pdf/2006.13205.pdf
带有目标条件层次预测器的远景视觉规划
https://www.bilibili.com/video/BV1Lz4y1X7Vx

Show me the Way: Intrinsic Motivation from Demonstrations
https://arxiv.org/abs/2006.12917
告诉我方法:来自演示的内在动机

Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
https://arxiv.org/pdf/2002.05616.pdf
学习斯坦因差异训练和评估能量模型无抽样

MLSS
http://mlss.tuebingen.mpg.de/2020/

AvE: Assistance via Empowerment
https://arxiv.org/abs/2006.14796

Machine Learning with Membership Privacy using Adversarial Regularization
https://arxiv.org/abs/1807.05852
https://www.bilibili.com/video/BV1L7411K7iH/

"They Say, I Say" model for Survey & Related Works.
https://www.bilibili.com/video/BV1b54y1q7Vz

Graph Structure of Neural Networks
https://proceedings.icml.cc/static/paper_files/icml/2020/201-Paper.pdf
https://www-cs.stanford.edu/~jure/pubs/nn_structure-icml20.pdf
https://www.bilibili.com/video/BV1yz4y1D7fn

Bandit Algorithm
https://tor-lattimore.com/downloads/book/book.pdf

Contrastive Learning: A brief overview
https://res.mdpi.com/d_attachment/technologies/technologies-09-00002/article_deploy/technologies-09-00002-v2.pdf
https://arxiv.org/abs/2011.00362