Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates

01/14/2021
by   Zengyi Qin, et al.
0

We study the multi-agent safe control problem where agents should avoid collisions to static obstacles and collisions with each other while reaching their goals. Our core idea is to learn the multi-agent control policy jointly with learning the control barrier functions as safety certificates. We propose a novel joint-learning framework that can be implemented in a decentralized fashion, with generalization guarantees for certain function classes. Such a decentralized framework can adapt to an arbitrarily large number of agents. Building upon this framework, we further improve the scalability by incorporating neural network architectures that are invariant to the quantity and permutation of neighboring agents. In addition, we propose a new spontaneous policy refinement method to further enforce the certificate condition during testing. We provide extensive experiments to demonstrate that our method significantly outperforms other leading multi-agent control approaches in terms of maintaining safety and completing original tasks. Our approach also shows exceptional generalization capability in that the control policy can be trained with 8 agents in one scenario, while being used on other scenarios with up to 1024 agents in complex multi-agent environments and dynamics.

READ FULL TEXT
research
03/23/2021

Safe Multi-Agent Reinforcement Learning through Decentralized Multiple Control Barrier Functions

Multi-Agent Reinforcement Learning (MARL) algorithms show amazing perfor...
research
09/19/2023

Learning Adaptive Safety for Multi-Agent Systems

Ensuring safety in dynamic multi-agent systems is challenging due to lim...
research
08/10/2020

Multi-Agent Safe Planning with Gaussian Processes

Multi-agent safe systems have become an increasingly important area of s...
research
02/27/2023

Safe Multi-agent Learning via Trapping Regions

One of the main challenges of multi-agent learning lies in establishing ...
research
07/13/2023

Discovering How Agents Learn Using Few Data

Decentralized learning algorithms are an essential tool for designing mu...
research
05/22/2023

Risk-aware Safe Control for Decentralized Multi-agent Systems via Dynamic Responsibility Allocation

Decentralized control schemes are increasingly favored in various domain...
research
05/30/2023

Distributed Hierarchical Distribution Control for Very-Large-Scale Clustered Multi-Agent Systems

As the scale and complexity of multi-agent robotic systems are subject t...

Please sign up or login with your details

Forgot password? Click here to reset