Waris Radji

A simple example of the use of Vegas with the Polynote, the new notebook created by Netflix.

Feature/call hierarchy

4

Here is the PR related to the call hierarchy feature #4044. Here is the list of features that I'm working on and their status , feel free to suggest others...

Universal Adversarial Perturbations

1

Hello, I would like to implement the [universal adversarial perturbations](https://arxiv.org/abs/1610.08401) algorithm in this library. This library was designed to compute perturbed images, but this method returns a universal vector created...

# Description I don't think that the current way indicated in the documentation is the right way to prevent stable-baselines3 from normalizing the images. I've updated the documentation, with a...

[Question] Is `ActionBonus` wrapper correct ?

1

`ActionBonus` is a wrapper that adds an exploration bonus to less visited (state,action) pairs. Regarding the code source, we make the transition to the new state s_{t+1} before updating the...

Impossible to convert from obographs .json

3

With the latest robot.jar. I got this error when I try to convert a json file to owl (``robot convert -i abox.json -o test.owl -vvv ): ``` DEBUG Loading ontology...

Fix slow multiprocessing

2

## Description This PR refer to #329 - \[ ] Add regression test - \[ ] Add torch.multiprocessing - \[ ] Add regression test Add joblib manager ?

[Suggestion] Add type hints

2

I think adding type hinting can improve the overall quality of *rlberry*, but it will be a huge work. What do you think ?

Several people have implemented their own algorithm in RLBerry, that lead to different naming of the same concepts in the docs or variables names. We should be consistent in the...

Hey, I will add the experimental agent **IMED-RL** from the paper *IMED-RL: Regret optimal learning of ergodic Markov decision processes*, Fabien Pesquerel, Odalric-Ambrym Maillard This is a learning policy that...