<abstract xmlns="http://www.w3.org/1999/xhtml">

<p><sup>1</sup>Most reinforcement learning benchmarks – especially in multi-agent tasks – do not go beyond observations with simple noise; nonetheless, real scenarios induce more elaborate vision pipeline failures: false sightings, misclassifications or occlusion. In this work, we propose a lightweight, 2D environment for robot soccer and autonomous driving that can emulate the above discrepancies. Besides establishing a benchmark for accessible multi-agent reinforcement learning research, our work addresses the challenges the simulator imposes. For handling realistic noise, we use self-supervised learning to enhance scene reconstruction and extend curiosity-driven learning to model longer horizons. Our extensive experiments show that the proposed methods achieve state-of-the-art performance, compared against actor-critic methods, ICM, and PPO.</p>
</abstract>

1Most reinforcement learning benchmarks – especially in multi-agent tasks – do not go beyond observations with simple noise; nonetheless, real scenarios induce more elaborate vision pipeline failures: false sightings, misclassifications or occlusion. In this work, we propose a lightweight, 2D environment for robot soccer and autonomous driving that can emulate the above discrepancies. Besides establishing a benchmark for accessible multi-agent reinforcement learning research, our work addresses the challenges the simulator imposes. For handling realistic noise, we use self-supervised learning to enhance scene reconstruction and extend curiosity-driven learning to model longer horizons. Our extensive experiments show that the proposed methods achieve state-of-the-art performance, compared against actor-critic methods, ICM, and PPO.

Handling Realistic Noise in Multi-Agent Systems with Self-Supervised Learning and Curiosity

Department of Control Engineering and Information Technology

Budapest University of Technology and Economics

Journal of Artificial Intelligence and Soft Computing Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

1Most reinforcement learning benchmarks – especially in multi-agent tasks – do not go beyond observations with simple noise; nonetheless, real scenarios induce...

Handling Realistic Noise in Multi-Agent Systems with Self-Supervised Learning and Curiosity

Publié en ligne: 23 févr. 2022

Pages: 135 - 148

Reçu: 27 sept. 2021

Accepté: 18 déc. 2021

DOI: https://doi.org/10.2478/jaiscr-2022-0009

Mots clés
deep reinforcement learning, multi-agent environment, autonomous driving, robot soccer, self-supervised learning

© 2022 Márton Szemenyei et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Handling Realistic Noise in Multi-Agent Systems with Self-Supervised Learning and Curiosity

Publié en ligne: 23 févr. 2022

Pages: 135 - 148

Reçu: 27 sept. 2021

Accepté: 18 déc. 2021

DOI: https://doi.org/10.2478/jaiscr-2022-0009

Mots clésdeep reinforcement learning, multi-agent environment, autonomous driving, robot soccer, self-supervised learning

© 2022 Márton Szemenyei et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Mots clés
deep reinforcement learning, multi-agent environment, autonomous driving, robot soccer, self-supervised learning