DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems

06/28/2022
by   Joe Eappen, et al.
2

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 the need to (a) craft specification primitives that allow expression and interplay of both local and global objectives, (b) tame explosion in the state and action spaces to enable effective learning, and (c) minimize coordination frequency and the set of engaged participants for global objectives. To address these challenges, we propose a novel specification framework that allows natural composition of local and global objectives used to guide training of a multi-agent system. Our technique enables learning expressive policies that allow agents to operate in a coordination-free manner for local objectives, while using a decentralized communication protocol for enforcing global ones. Experimental results support our claim that sophisticated multi-agent distributed planning problems can be effectively realized using specification-guided learning.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/13/2018

Coordination-driven learning in multi-agent problem spaces

We discuss the role of coordination as a direct learning objective in mu...
research
08/06/2020

The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning

Many real-world problems require the coordination of multiple autonomous...
research
05/08/2021

Scalable, Decentralized Multi-Agent Reinforcement Learning Methods Inspired by Stigmergy and Ant Colonies

Bolstering multi-agent learning algorithms to tackle complex coordinatio...
research
02/06/2019

Distributed Synthesis of Surveillance Strategies for Mobile Sensors

We study the problem of synthesizing strategies for a mobile sensor netw...
research
02/13/2012

Decentralized Multi-agent Plan Repair in Dynamic Environments

Achieving joint objectives by teams of cooperative planning agents requi...
research
06/21/2021

Curriculum-Driven Multi-Agent Learning and the Role of Implicit Communication in Teamwork

We propose a curriculum-driven learning strategy for solving difficult m...
research
09/08/2019

An Architectural Style for Self-Adaptive Multi-Agent Systems

Modern distributed software systems often operate in dynamic environment...

Please sign up or login with your details

Forgot password? Click here to reset