Practical_RL/week9_policy_II at master · pb-pravin/Practical_RL · GitHub

Name		Name	Last commit message	Last commit date
parent directory ..
README.md		README.md
seminar_TRPO_pytorch.ipynb		seminar_TRPO_pytorch.ipynb
seminar_TRPO_tensorflow.ipynb		seminar_TRPO_tensorflow.ipynb
seminar_TRPO_theano.ipynb		seminar_TRPO_theano.ipynb

README.md

Materials

This section covers some steroids for policy gradient methods, along with a cool general trick called

Lecture on NPG and TRPO by J. Schulman - video
Alternative lecture on TRPO and open problems by... J. Schulman - video
Our videos: lecture, seminar (russian)
Original articles - TRPO, NPG

Practice

Go to seminar_TRPO_<framework>.ipynb and follow instructions in the notebook.

More: Reinforcement learning in large/continuous action spaces

While you already know algorithms that will work with continuously many actions, it can't hurt to learn something more specialized.

Lecture by J. Schulman - video
Q-learning with normalized advantage functions - article, code1, code2
Deterministic policy gradient - article, post+code
Stochastic value gradient - article
Embedding large discrete action spaces for RL - article
Lecture by A. Seleznev, 5vision (russian) - video