Cooperative Control of Mobile Robots with Stackelberg Learning

TL;DR

This paper introduces SLiCC, a novel deep reinforcement learning method for multi-robot cooperation that models decision-making as Stackelberg bimatrix games to improve collective utility.

Contribution

SLiCC is the first approach to integrate Stackelberg game theory with deep reinforcement learning for cooperative multi-robot control.

Findings

SLiCC outperforms centralized multi-agent Q-learning in a bi-robot transportation task.

SLiCC effectively models asymmetric agent preferences and capabilities.

The method achieves higher combined utility in cooperative scenarios.

Abstract

Multi-robot cooperation requires agents to make decisions that are consistent with the shared goal without disregarding action-specific preferences that might arise from asymmetry in capabilities and individual objectives. To accomplish this goal, we propose a method named SLiCC: Stackelberg Learning in Cooperative Control. SLiCC models the problem as a partially observable stochastic game composed of Stackelberg bimatrix games, and uses deep reinforcement learning to obtain the payoff matrices associated with these games. Appropriate cooperative actions are then selected with the derived Stackelberg equilibria. Using a bi-robot cooperative object transportation problem, we validate the performance of SLiCC against centralized multi-agent Q-learning and demonstrate that SLiCC achieves better combined utility.