Essential Site Maintenance: Authorea-powered sites will be updated circa 15:00-17:00 Eastern on Tuesday 5 November.
There should be no interruption to normal services, but please contact us at [email protected] in case you face any issues.

loading page

Constraint-Based Multi-Agent Reinforcement Learning for Collaborative Tasks
  • +1
  • xiumin shang,
  • Tengyu Xu,
  • Ioannis Karamouzas,
  • Marcelo Kallmann
xiumin shang
University of California Merced

Corresponding Author:[email protected]

Author Profile
Tengyu Xu
Meta Platforms Inc
Author Profile
Ioannis Karamouzas
Clemson University
Author Profile
Marcelo Kallmann
University of California Merced
Author Profile

Abstract

In order to be successfully executed, collaborative tasks performed by two agents often require a cooperative strategy to be learned. In this work, we propose a constraint-based multi-agent reinforcement learning approach called Constrained Multi-agent Soft Actor Critic (C-MSAC) to train control policies for simulated agents performing collaborative multi-phase tasks. Given a task with n phases, the first n-1 phases are treated as constraints for the final task phase objective, which is addressed with a centralized training and decentralized execution approach. We highlight our framework on a tray balancing task including two phases: tray lifting and cooperative tray control for target following. We evaluate our proposed approach and compare it against its unconstrained variant (MSAC). The performed comparisons show that C-MSAC leads to higher success rates, more robust control policies, and better generalization performance.
27 Apr 2023Submitted to Computer Animation and Virtual Worlds
02 May 2023Submission Checks Completed
02 May 2023Assigned to Editor
02 May 2023Review(s) Completed, Editorial Evaluation Pending
02 May 2023Editorial Decision: Accept