Reinforcement Learning for Athletic Intelligence: Lessons from the 1st “AI Olympics with RealAIGym” Competition
Paper in proceeding, 2024

As artificial intelligence gains new capabilities, it becomes important to evaluate it on real-world tasks. In particular, the fields of robotics and reinforcement learning (RL) are lacking in standardized benchmarking tasks on real hardware. To facilitate reproducibility and stimulate algorithmic advancements, we held an AI Olympics competition at IJCAI 2023 conference based on the double pendulum system in the RealAIGym project where the participants were asked to develop a controller for the swing up and stabilization task. This paper presents the methods and results from the top participating teams and provides insights into the real-world performance of RL algorithms with respect to a baseline time-varying LQR controller.

Author

Felix Wiebe

Deutsches Forschungszentrum fur Kunstliche Intelligenz

Niccolò Turcato

University of Padua

Alberto Dalla Libera

University of Padua

Chi Zhang

Technical University of Munich

Theo Vincent

Deutsches Forschungszentrum fur Kunstliche Intelligenz

Shubham Vyas

Deutsches Forschungszentrum fur Kunstliche Intelligenz

Giulio Giacomuzzo

University of Padua

Ruggero Carli

University of Padua

Diego Romeres

Mitsubishi Electric Research Laboratories

Akhil Sathuluri

Technical University of Munich

Markus Zimmermann

Technical University of Munich

Boris Belousov

Deutsches Forschungszentrum fur Kunstliche Intelligenz

Jan Peters

Technische Universität Darmstadt

Centre for Cognitive Science

Hessian.AI

Deutsches Forschungszentrum fur Kunstliche Intelligenz

Frank Kirchner

Deutsches Forschungszentrum fur Kunstliche Intelligenz

Universität Bremen

Shivesh Kumar

Deutsches Forschungszentrum fur Kunstliche Intelligenz

Chalmers, Mechanics and Maritime Sciences (M2), Dynamics

Other publications Research

IJCAI International Joint Conference on Artificial Intelligence

10450823 (ISSN)

8833-8837
9781956792041 (ISBN)

33rd International Joint Conference on Artificial Intelligence, IJCAI 2024
Jeju, South Korea,

Subject Categories

Robotics

Control Engineering

Computer Science

More information

Latest update

9/27/2024

Feedback and support

If you have questions, need help, find a bug or just want to give us feedback you may use this form, or contact us per e-mail research.lib@chalmers.se.

About

Research.chalmers.se contains research information from Chalmers University of Technology, Sweden. It includes information on projects, publications, research funders and collaborations.

More about coverage period and what is publicly available

Privacy and cookies

Accessibility

Citation Style Language
citeproc-js (Frank Bennett)

Links

Chalmers Library
Chalmers Research
Chalmers Student Theses

Chalmers University of Technology

SE-412 96 GOTHENBURG, SWEDEN
PHONE: +46 (0)31-772 10 00
WWW.CHALMERS.SE