Sequential Order Adjustment of Action Decisions for Multi-Agent Transformer (Student Abstract)
Shota Takayama, Katsuhide Fujita
Abstract
Multi-agent reinforcement learning (MARL) trains multiple agents in shared environments. Recently, MARL models have significantly improved performance by leveraging sequential decision-making processes. Although these models can enhance performance, they do not explicitly con-sider the importance of the order in which agents make decisions. We propose AOAD-MAT, a novel model incorporating action decision sequence into learning. AOAD-MAT uses a Transformer-based actor-critic architecture to dynamically adjust agent action order. It introduces a subtask predicting the next agent to act, integrated into a PPO-based loss function. Experiments on StarCraft Multi-Agent Challenge and Multi-Agent MuJoCo benchmarks show AOAD-MAT out-performs existing models, demonstrating the effectiveness of adjusting agent order in MARL.
BibTeX
@article{Takayama_Fujita_2025, title={Sequential Order Adjustment of Action Decisions for Multi-Agent Transformer (Student Abstract)}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/35306}, DOI={10.1609/aaai.v39i28.35306}, abstractNote={Multi-agent reinforcement learning (MARL) trains multiple agents in shared environments. Recently, MARL models have significantly improved performance by leveraging sequential decision-making processes. Although these models can enhance performance, they do not explicitly con-sider the importance of the order in which agents make decisions. We propose AOAD-MAT, a novel model incorporating action decision sequence into learning. AOAD-MAT uses a Transformer-based actor-critic architecture to dynamically adjust agent action order. It introduces a subtask predicting the next agent to act, integrated into a PPO-based loss function. Experiments on StarCraft Multi-Agent Challenge and Multi-Agent MuJoCo benchmarks show AOAD-MAT out-performs existing models, demonstrating the effectiveness of adjusting agent order in MARL.}, number={28}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Takayama, Shota and Fujita, Katsuhide}, year={2025}, month={Apr.}, pages={29509-29511} }