Attention-Augmented Inverse Reinforcement Learning with Graph Convolutions for Multi-Agent Task Allocation
This work addresses inefficiencies in dynamic environments for applications like logistics and robotic coordination, though it appears incremental as it builds on existing IRL and attention methods.
The paper tackles the problem of multi-agent task allocation by proposing an inverse reinforcement learning framework that incorporates attention mechanisms to reduce reliance on manually designed reward functions and improve efficiency, with experiments showing superiority over existing methods in cumulative rewards and task execution efficiency.
This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Multi-agent task allocation (MATA) plays a vital role in cooperative multi-agent systems, with significant implications for applications such as logistics, search and rescue, and robotic coordination. Although traditional deep reinforcement learning (DRL) methods have been shown to be promising, their effectiveness is hindered by a reliance on manually designed reward functions and inefficiencies in dynamic environments. In this paper, an inverse reinforcement learning (IRL)-based framework is proposed, in which multi-head self-attention (MHSA) and graph attention mechanisms are incorporated to enhance reward function learning and task execution efficiency. Expert demonstrations are utilized to infer optimal reward densities, allowing dependence on handcrafted designs to be reduced and adaptability to be improved. Extensive experiments validate the superiority of the proposed method over widely used multi-agent reinforcement learning (MARL) algorithms in terms of both cumulative rewards and task execution efficiency.