Modular Reinforcement Learning For Cooperative Swarms

• URL: http://arxiv.org/abs/2605.04939v1
• Date: Wed, 06 May 2026 14:05:36 GMT
• Title: Modular Reinforcement Learning For Cooperative Swarms
• Abstract summary: A cooperative robot swarm is a collective of computationally-limited robots that share a common goal.<n>Recent advances in distributed multi-agent reinforcement learning have demonstrated that it is possible for robots to learn how to interact effectively with others.<n>This paper proposes an alternative approach for representing spatial interaction states for reinforcement learning in swarms.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Autonomous Human-Robot Interaction via Operator Imitation [3.650193138379926]
  We propose to create autonomous interactive robots, by training a model to imitate operator data.<n>Our model is trained on a dataset of human-robot interactions.<n>We show that our method enables simple autonomous human-robot interactions comparable to the expert-operator baseline.
  arXiv  Detail & Related papers  (2025-04-03T16:06:44Z)
• Generalized Robot Learning Framework [10.03174544844559]
  We present a low-cost robot learning framework that is both easily reproducible and transferable to various robots and environments. We demonstrate that deployable imitation learning can be successfully applied even to industrial-grade robots.
  arXiv  Detail & Related papers  (2024-09-18T15:34:31Z)
• Correspondence learning between morphologically different robots via task demonstrations [2.1374208474242815]
  We propose a method to learn correspondences among two or more robots that may have different morphologies. A fixed-based manipulator robot with joint control and a differential drive mobile robot can be addressed within the proposed framework. We provide a proof-of-the-concept realization of correspondence learning between a real manipulator robot and a simulated mobile robot.
  arXiv  Detail & Related papers  (2023-10-20T12:42:06Z)
• ImitationNet: Unsupervised Human-to-Robot Motion Retargeting via Shared Latent Space [9.806227900768926]
  This paper introduces a novel deep-learning approach for human-to-robot motion. Our method does not require paired human-to-robot data, which facilitates its translation to new robots. Our model outperforms existing works regarding human-to-robot similarity in terms of efficiency and precision.
  arXiv  Detail & Related papers  (2023-09-11T08:55:04Z)
• Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning [54.636562516974884]
  In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on. In this work, we propose MEDAL++, a novel design for self-improving robotic systems. The robot autonomously practices the task by learning to both do and undo the task, simultaneously inferring the reward function from the demonstrations.
  arXiv  Detail & Related papers  (2023-03-02T18:51:38Z)
• Generalizable Human-Robot Collaborative Assembly Using Imitation Learning and Force Control [17.270360447188196]
  We present a system for human-robot collaborative assembly using learning from demonstration and pose estimation. The proposed system is demonstrated using a physical 6 DoF manipulator in a collaborative human-robot assembly scenario.
  arXiv  Detail & Related papers  (2022-12-02T20:35:55Z)
• A Capability and Skill Model for Heterogeneous Autonomous Robots [69.50862982117127]
  capability modeling is considered a promising approach to semantically model functions provided by different machines. This contribution investigates how to apply and extend capability models from manufacturing to the field of autonomous robots.
  arXiv  Detail & Related papers  (2022-09-22T10:13:55Z)
• REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer [57.045140028275036]
  We consider the problem of transferring a policy across two different robots with significantly different parameters such as kinematics and morphology. Existing approaches that train a new policy by matching the action or state transition distribution, including imitation learning methods, fail due to optimal action and/or state distribution being mismatched in different robots. We propose a novel method named $REvolveR$ of using continuous evolutionary models for robotic policy transfer implemented in a physics simulator.
  arXiv  Detail & Related papers  (2022-02-10T18:50:25Z)
• Spatial Computing and Intuitive Interaction: Bringing Mixed Reality and Robotics Together [68.44697646919515]
  This paper presents several human-robot systems that utilize spatial computing to enable novel robot use cases. The combination of spatial computing and egocentric sensing on mixed reality devices enables them to capture and understand human actions and translate these to actions with spatial meaning.
  arXiv  Detail & Related papers  (2022-02-03T10:04:26Z)
• Lifelong Robotic Reinforcement Learning by Retaining Experiences [61.79346922421323]
  Many multi-task reinforcement learning efforts assume the robot can collect data from all tasks at all times. In this work, we study a practical sequential multi-task RL problem motivated by the practical constraints of physical robotic systems. We derive an approach that effectively leverages the data and policies learned for previous tasks to cumulatively grow the robot's skill-set.
  arXiv  Detail & Related papers  (2021-09-19T18:00:51Z)
• Learning Predictive Models From Observation and Interaction [137.77887825854768]
  Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works. However, learning a model that captures the dynamics of complex skills represents a major challenge. We propose a method to augment the training set with observational data of other agents, such as humans.
  arXiv  Detail & Related papers  (2019-12-30T01:10:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.