Shota Takayama — accepted AI-conference papers

2026

CtoD-MAT: Bridging Centralized and Decentralized Execution in Multi-Agent Reinforcement Learning (Student Abstract)

AAAI 2026technical

Although centralized training with centralized execution (CTCE) excels at multi-agent coordination, its reliance on global information limits its use in the real world. Conversely, the practical decentralized execution (CTDE) paradigm often struggles with complex coordination. This paper bridges thi

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Sequential Order Adjustment of Action Decisions for Multi-Agent Transformer (Student Abstract)

Shota Takayama, Katsuhide Fujita

AAAI 2025technical

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…

Cited by 0 Source ↗PDF ↗Scholar ↗