Kouki Nakagami
Papers
1
Total Citations
3
H-Index
1
About
Kouki Nakagami is a rising researcher in artificial intelligence, with a focused expertise in multi-agent reinforcement learning (MARL) and deep reinforcement learning architectures. His most-cited work, "A Study for Comparative Analysis of Dueling DQN and Centralized Critic Approaches in Multi-Agent Reinforcement Learning" (2024), makes a significant contribution by introducing a deep Q-network agent that employs a dueling architecture. This innovative approach refines action valuation by decoupling the estimation of state-value and action-value functions, a technique adapted to enable multiple agents to operate concurrently within a shared environment. Nakagami’s research directly addresses the critical challenge of coordination and efficient learning in complex, multi-agent systems. While his career is in its early stages, his work is already garnering attention (3 citations), demonstrating its relevance to the cutting-edge field of MARL. His comparative analysis of dueling DQN against centralized critic methods provides a valuable framework for future research, positioning him as a promising contributor to the development of more sophisticated and scalable AI systems capable of collaborative decision-making.
Research Focus
Key Achievements
Top Papers
- 1