Practical_RL/week8_scst at master · defstryker/Practical_RL · GitHub

Name		Name	Last commit message	Last commit date
parent directory ..
README.md		README.md
basic_model_tf.py		basic_model_tf.py
basic_model_theano.py		basic_model_theano.py
basic_model_torch.py		basic_model_torch.py
bonus.ipynb		bonus.ipynb
he-pron-wiktionary.txt		he-pron-wiktionary.txt
main_dataset.txt		main_dataset.txt
practice_tf.ipynb		practice_tf.ipynb
practice_theano.ipynb		practice_theano.ipynb
practice_torch.ipynb		practice_torch.ipynb
scheme.svg		scheme.svg
voc.py		voc.py

README.md

Materials

Slides
Our lecture & seminar (russian)
English lectures
- Lecture by Mohammad Norouzi - cs294 video
- Optional lecture on conversation systems - video
Will hopefully record our lecture in english soon!
Self-critical sequence traning original article

Practice

As usual, go to practice_{your framework}.ipynb above and follow instructions from there. pytorch, tensorflow, theano

Binder quickstart (lasts 1 hour):

More materials

An awesome post explaining attention and long-term memory models.
BLEU and CIDEr articles.
Image captioning
- MSCOCO captioning challenge
- Captioning baseline notebook
Other articles on reinforcement learning for natural language:
- task-oriented conversation system
- generating dialogues
- sequential adversarial networks (a.k.a. SeqGAN)
- A large overview for machine translation (touching on RL, including RL failures) - arxiv
- How not to evaluate conversation models - arxiv
Overview of other non-games applications ("that article again") - arxiv