CatlNet: Learning Communication and Coordination Policies from CaTL+ Specifications

2022-11-30 · Wenliang Liu, Kevin Leahy, Zachary Serlin, Calin Belta

In this paper, we propose a learning-based framework to simultaneously learn the communication and distributed control policies for a heterogeneous multi-agent system (MAS) under complex mission requirements from Capability Temporal Logic plus (CaTL+) specifications. Both policies are trained, implemented, and deployed using a novel neural network model called CatlNet. Taking advantage of the robustness measure of CaTL+, we train CatlNet centrally to maximize it where network parameters are shared among all agents, allowing CatlNet to scale to large teams easily. CatlNet can then be deployed distributedly. A plan repair algorithm is also introduced to guide CatlNet's training and improve both training efficiency and the overall performance of CatlNet. The CatlNet approach is tested in simulation and results show that, after training, CatlNet can steer the decentralized MAS system online to satisfy a CaTL+ specification with a high success rate.

📄 PDF Abstract BibTeX arXiv:2212.11792

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Repair 설명 없음

MAS This optimizer mix ADAM and SGD creating the MAS optimizer.

Robust Multi-Agent Coordination from CaTL+ Specifications

2022-10-04 · Wenliang Liu, Kevin Leahy, Zachary Serlin, Calin Belta

We consider the problem of controlling a heterogeneous multi-agent system required to satisfy temporal logic requirements. Capability Temporal Logic (CaTL) was recently proposed to formalize such specifications for deplo…

Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation

2026-06-17 · Ahmad Farooq, Kamran Iqbal arxiv

Multi-agent reinforcement learning (MARL) enables agents to develop coordination strategies through emergent communication, but neural policies lack the formal safety guarantees required for safety-critical robotic deplo…

Multi-agent Reinforcement Learning

DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems

2022-06-28 · Joe Eappen, Suresh Jagannathan

While notable progress has been made in specifying and learning objectives for general cyber-physical systems, applying these methods to distributed multi-agent systems still pose significant challenges. Among these are …

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Towards an Open Source Finite-State Morphological Analyzer for Zacatlán-Ahuacatlán-Tepetzintla Nahuatl

2021-03-01 · ComputEL 2021 3 · Robert Pugh, Francis Tyers

Capability Augmentation for Heterogeneous Dynamic Teaming with Temporal Logic Tasks

2024-09-14 · Carter Berlind, Wenliang Liu, Alyssa Pierson, Calin Belta

This paper considers how heterogeneous multi-agent teams can leverage their different capabilities to mutually improve individual agent performance. We present Capability-Augmenting Tasks (CATs), which encode how agents …