This repository is a clone of the Spring 2017 deep reinforcement learning class at Berkeley. We've cloned it for the purpose of having a collaborative study group watching the lectures and working on the problem sets.
-
Google's deep learning Udacity course seems like a good introduction.
-
Professor Bertsekas's Dynamic Programming lectures seem like a good supplement to these lectures.
- Yann Lecun's paper discusses tricks for normalization and initialization.
- A post describing RNNs.
- A post explaining LSTMs.
- A pair of posts on seq2seq and attention.
- A post giving general background on RL and diving into score function gradient estimators.
-
Tensorboard seems like a good way to instrument training algorithms.
-
TF Slim might save time.
- Pudb seems like a useful debug tool.
- Stanford CS class CS231n: Convolutional Neural Networks for Visual Recognition - another class more focused on convnets