mlsanityData to 14 Oct 2026

Robust synchronization and policy adaptation for networked heterogeneous agents

arXiv 2409.03273 ↗First posted 5 Sep 2024eess.SY cs.SYcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

We propose a robust adaptive online synchronization method for leader-follower networks of nonlinear heterogeneous agents with system uncertainties and input magnitude saturation. Synchronization is achieved using a Distributed input Magnitude Saturation Adaptive Control with Reinforcement Learning (DMSAC-RL), which improves the empirical performance of policies trained on off-the-shelf models using Reinforcement Learning (RL) strategies. The leader observes the performance of a reference model, and followers observe the states and actions of the agents they are connected to, but not the reference model. The leader and followers may differ from the reference model in which the RL control policy was trained. DMSAC-RL uses an internal loop that adjusts the learned policy for the agents in the form of augmented input to solve the distributed control problem, including input-matched uncertainty parameters. We show that the synchronization error of the heterogeneous network is Uniformly Ultimately Bounded (UUB). Numerical analysis of a network of Multiple Input Multiple Output (MIMO) systems supports our theoretical findings.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 13 of its 31 references that are in the map. First posted on arXiv 5 Sep 2024.

Builds on

13 of 31 references.

References · 13

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
  3. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 319
  4. 2018A Tour of Reinforcement Learning: The View from Continuous Controlcited by 151
  5. 2018Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applicationscited by 127
  6. 2017The Internet of Battle Thingscited by 11
  7. 2018Tutorial on dynamic average consensus: the problem, its applications, and the algorithmscited by 9
  8. 2019Connections Between Adaptive Control and Optimization in Machine Learningcited by 7
  9. 2021Online Policies for Real-Time Control Using MRAC-RLcited by 7
  10. 2014Nonasymptotic Convergence Rates for Cooperative Learning Over Time-Varying Directed Graphscited by 6
  11. 2020MRAC-RL: A Framework for On-Line Policy Adaptation Under Parametric Model Uncertaintycited by 2
  12. 2020Adaptive Synchronization of Heterogeneous Multi-Agent Systems: A Free Observer Approachcited by 1
1 more
  1. 2024An Application of Model Reference Adaptive Control for Multi-Agent Synchronization in Drone Networkscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Distributed Actor-Critic Algorithm for Fixed-Time Consensus in Nonlinear Multi-Agent Systems ↗
  2. 2025Model Reference Adaptive Control of Networked Systems with State and Input Delays
  3. 2025Emergent Coordination and Phase Structure in Independent Multi-Agent Reinforcement Learning
  4. 2025Robust Remote Reinforcement Learning over Unreliable Communication Channels using Homomorphic State Encoding
  5. 2025GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning
  6. 2026Decoupled Delay Compensation: Enhancing Pre-trained MARL Policies via Learned Dynamics Filtering
  7. 2026Reinforcement Learning for Control Systems with Time Delays: A Comprehensive Survey
  8. 2026SparseRL-Sync: Lossless Weight Synchronization with ~100x Less Communication