MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding

10/25/2019
by   Wenbo Zhang, et al.
0

Reinforcement learning is a promising approach to learning control policies for performing complex multi-agent robotics tasks. However, a policy learned in simulation often fails to guarantee even simple safety properties such as obstacle avoidance. To ensure safety, we propose multi-agent model predictive shielding (MAMPS), an algorithm that provably guarantees safety for an arbitrary learned policy. In particular, it operates by using the learned policy as often as possible, but instead uses a backup policy in cases where it cannot guarantee the safety of the learned policy. Using a multi-agent simulation environment, we show how MAMPS can achieve good performance while ensuring safety.

READ FULL TEXT

page 1

page 2

page 3

page 4

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
08/11/2020

Analysis of Agricultural Policy Recommendations using Multi-Agent Systems

Despite agriculture being the primary source of livelihood for more than...
research
01/20/2022

Safety-Aware Multi-Agent Apprenticeship Learning

Our objective of this project is to make the extension based on the tech...
research
10/25/2021

Safely Bridging Offline and Online Reinforcement Learning

A key challenge to deploying reinforcement learning in practice is explo...
research
11/21/2022

Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning

Oversubscription is a common practice for improving cloud resource utili...
research
11/14/2021

Relative Distributed Formation and Obstacle Avoidance with Multi-agent Reinforcement Learning

Multi-agent formation as well as obstacle avoidance is one of the most a...
research
12/18/2020

A Distributed Simplex Architecture for Multi-Agent Systems

We present Distributed Simplex Architecture (DSA), a new runtime assuran...

Please sign up or login with your details

Forgot password? Click here to reset