English

SaLinA: Sequential Learning of Agents

Machine Learning 2021-10-18 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-24T06:54:44.660Z