- implement NPI
- learn GAN
- learn DQN
Working Folder:
- article on meta learning and GAN: https://medium.com/intuitionmachine/predictive-learning-is-the-key-to-deep-learning-acceleration-93e063195fd0#.199h0hdmi
- collection of GAN and VAE example in both
TensorFlowandpyTorch: https://github.com/wiseodd/generative-models
- OpenAI Gym
- Learning to navigate in complex environments: https://arxiv.org/abs/1611.03673
- RL with unsupervised Auxiliary Tasks: https://arxiv.org/abs/1611.05397
- talk video: https://www.quora.com/What-do-you-think-about-reinforcement-learning-Is-it-the-cherry-on-the-cake-as-Yann-LeCun-puts-it-1
- Sutton's new work: https://www.quora.com/What-are-the-rumours-I-hear-about-Prof-Rich-Suttons-upcoming-work-which-is-about-to-change-the-face-of-Reinforcement-Learning
- A russian course Practical RL: https://github.com/yandexdataschool/Practical_RL
- Berkeley CS294: http://rll.berkeley.edu/deeprlcourse/
- 224 Course N: https://github.com/stanfordnlp/cs224n-winter17-notes