Takuma Seno

Papers

Total Citations

H-Index

About

Takuma Seno is a researcher at the forefront of artificial intelligence, with a primary focus on reinforcement learning and its application to autonomous systems. His most notable contribution is the development of a super-human, vision-based reinforcement learning agent for autonomous racing in the high-fidelity simulator Gran Turismo. This groundbreaking work, published in 2024, achieved a longstanding grand challenge by outpacing the best human drivers, demonstrating the immense potential of end-to-end deep reinforcement learning in complex, real-time environments. Beyond this headline achievement, Seno has also explored the domain of shared autonomy, investigating how semi-autonomous agents, such as mobile robots, can adapt to human users through feedback to reduce operational load. His research on adaptive agents via episodic control, published in 2018, lays foundational groundwork for human-robot collaboration. While his citation counts are currently modest, the impact of his super-human racing agent is poised to be transformative, influencing both the fields of AI and robotics by pushing the boundaries of what autonomous systems can achieve.