MushroomRL: Simplifying Reinforcement Learning Research

Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters
1/4/2020
cs.LGstat.ML
rl

Official code: MushroomRL/mushroom-rl (944 stars, MIT, PyTorch, last commit 2026-10-20).

Abstract

MushroomRL is an open-source Python library developed to simplify the process of implementing and running Reinforcement Learning (RL) experiments. Compared to other available libraries, MushroomRL has been created with the purpose of providing a comprehensive and flexible framework to minimize the effort in implementing and testing novel RL methodologies. Indeed, the architecture of MushroomRL is built in such a way that every component of an RL problem is already provided, and most of the time users can only focus on the implementation of their own algorithms and experiments. The result is a library from which RL researchers can significantly benefit in the critical phase of the empirical analysis of their works. MushroomRL stable code, tutorials and documentation can be found at https://github.com/MushroomRL/mushroom-rl.

View on arXivView PDF

Code Implementations(1)

MushroomRL/mushroom-rlOfficial100%
PyTorchMIT

Python library for Reinforcement Learning.

944165Python, MakefileFeb 25, 20174 days agoMIT
atariddpgdeep-learningdeep-reinforcement-learningdqn+9 more

Similar Papers

Baconian: A Unified Open-source Framework for Model-Based Reinforcement Learning

78% match1 repo1142019

NiceWebRL: a Python library for human subject experiments with reinforcement learning environments

78% match1 repo842025

QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration

77% match1 repo3612023

AndroidEnv: A Reinforcement Learning Platform for Android

76% match1 repo1.2k2021

CORL: Research-oriented Deep Offline Reinforcement Learning Library

76% match3 repos1.4k2022

GriddlyJS: A Web IDE for Reinforcement Learning

76% match2022

Cite this paper

@article{deramo2020mushroomrl,
  title  = {MushroomRL: Simplifying Reinforcement Learning Research},
  author = {Carlo D'Eramo and Davide Tateo and Andrea Bonarini and Marcello Restelli and Jan Peters},
  year   = {2020},
  eprint = {2001.01102},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2001.01102}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2001.01102.svg)](https://codeofpaper.com/paper/2001.01102)

Discussion