SaLinA is a simple library that makes implementing complex sequential learning models easy, including reinforcement learning algorithms. It is built as an extension of PyTorch: algorithms coded with \SALINA{} can be understood in few minutes by PyTorch users and modified easily. Moreover, SaLinA naturally works with multiple CPUs and GPUs at train and test time, thus being a good fit for the large-scale training use cases. In comparison to existing RL libraries, SaLinA has a very low adoption cost and capture a large variety of settings (model-based RL, batch RL, hierarchical RL, multi-agent RL, etc.). But SaLinA does not only target RL practitioners, it aims at providing sequential learning capabilities to any deep learning programmer.
@article{arxiv.2110.07910,
title = {SaLinA: Sequential Learning of Agents},
author = {Ludovic Denoyer and Alfredo de la Fuente and Song Duong and Jean-Baptiste Gaya and Pierre-Alexandre Kamienny and Daniel H. Thompson},
journal= {arXiv preprint arXiv:2110.07910},
year = {2021}
}