Open Source Reinforcement Learning

Open-source reinforcement learning (RL) environments are rapidly expanding, providing researchers with accessible tools to develop and test RL algorithms across diverse applications. Current research focuses on creating highly customizable and scalable environments for robotics (manipulation, navigation), structural design optimization, and chemical discovery, often employing model-free and model-based algorithms like Proximal Policy Optimization and DreamerV3, alongside evolutionary computation methods. The availability of these open-source platforms fosters collaboration, accelerates algorithm development, and facilitates the transfer of RL techniques to real-world problems, ultimately advancing both the field of AI and its practical applications.

Papers

July 10, 2024

Structural Design Through Reinforcement Learning
Thomas Rochefort-Beaudoin, Aurelian Vadean, Niels Aage, Sofiane Achiche
Proximal Policy Optimization Topology Optimization Empirical Game Structural Optimization Open Source Reinforcement Learning

December 21, 2023

Open-Source Reinforcement Learning Environments Implemented in MuJoCo with Franka Manipulator
Zichun Xu, Yuntao Li, Xiaohang Yang, Zhiyuan Zhao, Lei Zhuang, Jingdong Zhao
Serial Manipulator Multi Agent MuJoCo Multi Goal Reinforcement Learning Open Source Reinforcement Learning

November 13, 2023

TIAGo RL: Simulated Reinforcement Learning Environments with Tactile Data for Mobile Robots
Luca Lach, Francesco Ferro, Robert Haschke
Deep Reinforcement Learning Mobile Robot Tactile Data Tactile Based Open Source Reinforcement Learning

June 16, 2023

Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
Clément Bonnet, Daniel Luo, Donal Byrne, Shikha Surana, Sasha Abramowitz, Paul Duckworth, Vincent Coyette, Laurence I. Midgley, Elshadai Tegegn, Tristan Kalloniatis, Omayma Mahjoub, Matthew Macfarlane, Andries P. Smit, Nathan Grinsztajn, Raphael Boige, Cemlyn N. Waters, Mohamed A. Mimouni, Ulrich A. Mbou Sob, Ruan de Kock, Siddarth Singh, Daniel Furelos-Blanco, Victor Le, Arnu Pretorius, Alexandre Laterre
Reinforcement Learning Large Scale Actor Critic State of the Art JAX Compositional Diversity Open Source Reinforcement Learning

May 23, 2023

ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry
Chris Beeler, Sriram Ganapathi Subramanian, Kyle Sprague, Nouha Chatti, Colin Bellinger, Mitchell Shahen, Nicholas Paquin, Mark Baula, Amanuel Dawit, Zihan Yang, Xinkai Li, Mark Crowley, Isaac Tamblyn
Reinforcement Learning New Framework Chemical Discovery Open Source Reinforcement Learning

April 11, 2022

JORLDY: a fully customizable open source framework for reinforcement learning
Kyushik Min, Hyunho Lee, Kwansu Shin, Taehak Lee, Hojoon Lee, Jinwon Choi, Sungho Son
Reinforcement Learning Reinforcement Learning Algorithm Open Source Framework Reinforcement Learning Framework Open Source Reinforcement Learning

January 24, 2022

Pearl: Parallel Evolutionary and Reinforcement Learning Library
Rohan Tangri, Danilo P. Mandic, Anthony G. Constantinides
Reinforcement Learning Evolutionary Computation Reinforcement Learning Library Open Source Reinforcement Learning