Gal A. Kaminka: Publications

Sorted by DateClassified by Publication TypeClassified by TopicGrouped by Student (current)Grouped by Former Students

Modular Reinforcement Learning For Cooperative Swarms

Erel Shtossel and Gal A. Kaminka. Modular Reinforcement Learning For Cooperative Swarms. In Proceedings of the AAMAS Workshop on Autonomous Robots and Multirobot Systes (ARMS), 2026.

Download

(unavailable)

Abstract

A cooperative robot swarm is a collective of computationally-limited robots that share a common goal. Each robot can only interact with a small subset of its peers, without knowing how this affects the collective utility. Recent advances in distributed multi-agent reinforcement learning have demonstrated that it is possible for robots to learn how to interact effectively with others, in a manner that is aligned with the common goal, despite each robot learning independently of others. However, this requires each robot to represent a potentially combinatorial number of interaction states, challenging the memory capabilities of the robots. This paper proposes an alternative approach for representing spatial interaction states for multi-robot reinforcement learning in swarms. A modular (decomposed) representation is used, where each feature of the state is handled by a separate learning procedure, and the results aggregated. We demonstrate the efficacy of the approach in numerous experiments with simulated robot swarms carrying out foraging.

BibTeX

@inproceedings{arms26,
		title = {	Modular Reinforcement Learning For Cooperative Swarms},
		author = {Erel Shtossel and Gal A. Kaminka},
		booktitle = {Proceedings of the {AAMAS} Workshop on Autonomous Robots and Multirobot Systes ({ARMS})},
  	year = {2026},
  	abstract = {A cooperative robot swarm is a collective of computationally-limited robots that share a common goal. Each robot can only interact with a small subset of its peers, without knowing how this affects the collective utility. Recent advances in distributed multi-agent reinforcement learning have demonstrated that it is possible for robots to learn how to interact effectively with others, in a manner that is aligned with the common goal, despite each robot learning independently of others. However, this requires each robot to represent a potentially combinatorial number of interaction states, challenging the memory capabilities of the robots. This paper proposes an alternative approach for representing spatial interaction states for multi-robot reinforcement learning in swarms. A modular (decomposed) representation is used, where each feature of the state is handled by a separate learning procedure, and the results aggregated. We demonstrate the efficacy of the approach in numerous experiments with simulated robot swarms carrying out foraging. 
    },
}

Generated by bib2html.pl (written by Patrick Riley ) on Mon Apr 06, 2026 23:33:57