More tutorials are needed
codeman6688 opened this issue · comments
There are so few tutorials that novices don’t know how to use this library
We will be addressing this as soon as possible. Thank you for the feedback.
@rodrigodesalvobraz please keep the issues open until they are resolved.
People subscribe to github issues like this one as a way to be notified about the developments in the project.
@rodrigodesalvobraz please keep the issues open until they are resolved.
People subscribe to github issues like this one as a way to be notified about the developments in the project.
Thanks for pointing that out, I will do that.
A tutorial covering each of the cells in this table would be really helpful to get a sense of things:)
Docstrings and function signatures also really helpful.
Pearl Features | Recommender Systems | Auction Bidding | Creative Selection |
---|---|---|---|
Policy Learning | ✅ | ✅ | ✅ |
Intelligent Exploration | ✅ | ✅ | ✅ |
Safety | ✅ | ||
History Summarization | ✅ | ||
Replay Buffer | ✅ | ✅ | ✅ |
Contextual Bandit | ✅ | ||
Offline RL | ✅ | ✅ | |
Dynamic Action Space | ✅ | ✅ | |
Large-scale Neural Network | ✅ |
A tutorial covering each of the cells in this table would be really helpful to get a sense of things:) Docstrings and function signatures also really helpful.
Thank you, using the table as a guide is a really interesting suggestion. We are currently actively working on more tutorials. Please note that we have released a couple more recently. Here's the current list:
A single item recommender system. We derived a small contrived recommender system environment using the MIND dataset (Wu et al. 2020).
Contextual bandits. Demonstrates contextual bandit algorithms and their implementation using Pearl using a contextual bandit environment for providing data from UCI datasets, and tested the performance of neural implementations of SquareCB, LinUCB, and LinTS.
Frozen Lake. A simple example showing how to use a one-hot observation wrapper to learn the classic problem with DQN.
Deep Q-Learning (DQN) and Double DQN. Demonstrates how to run DQN and Double DQN on the Cart-Pole environment.