Kenta
Kawamoto

Profile

Kenta developed several robots at Sony, such as the first generation AIBO, small humanoid robot QRIO, and so on, where he worked on real-time embedded systems for those robots as a lead software engineer and system architect. Then he became interested in developmental intelligence of autonomous systems and started his research in this domain. He won the Best Paper Award at the International Conference on Development and Learning and Epigenetic Robotics 2011. At Sony R&D Center, he was leading and managing research on “behavior learning” which focuses on machine learning for planning and control of robot behaviors and skills. At Sony AI, Kenta is mainly involved in Game AI projects and was awarded the Sony Outstanding Engineer Award 2020.

Message

“I am very interested in achieving machine intelligence that is as flexible as a human being. I believe that 'intelligence’ lies in the ability to control the world. Perception and prediction alone are not enough to make a machine intelligent, in my humble opinion. In short, I’d like to live with a robot that learns autonomously and continuously to improve its behavior. I want the robot to be able to adapt not only to changes in the environment, but also to changes in the level of tasks and values, as such changes are the nature of human life and society. PlayStation's product-level games are the perfect place for the research and development of such intelligence.”

Publications

Skill-Critic: Refining Learned Skills for Hierarchical Reinforcement Learning

RAL, 2024
Ce Hao*, Catherine Weaver*, Chen Tang*, Kenta Kawamoto, Masayoshi Tomizuka*, Wei Zhan*

Hierarchical reinforcement learning (RL) can accelerate long-horizon decision-making by temporally abstracting a policy into multiple levels. Promising results in sparse reward environments have been seen with skills , i.e. sequences of primitive actions. Typically, a skill …

Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning

Nature, 2022
Peter Wurman, Samuel Barrett, Kenta Kawamoto, James MacGlashan, Kaushik Subramanian, Thomas Walsh, Roberto Capobianco, Alisa Devlic, Franziska Eckert, Florian Fuchs, Leilani Gilpin, Piyush Khandelwal, Varun Kompella, Hao Chih Lin, Patrick MacAlpine, Declan Oller, Takuma Seno, Craig Sherstan, Michael D. Thomure, Houmehr Aghabozorgi, Leon Barrett, Rory Douglas, Dion Whitehead Amago, Peter Dürr, Peter Stone, Michael Spranger, Hiroaki Kitano

Many potential applications of artificial intelligence involve making real-time decisions in physical systems while interacting with humans. Automobile racing represents an extreme example of these conditions; drivers must execute complex tactical manoeuvres to pass or block…

Expert Human-Level Driving in Gran Turismo Sport Using Deep Reinforcement Learning with Image-based Representation

NeurIPS, 2021
Ryuji Imamura, Takuma Seno, Kenta Kawamoto, Michael Spranger

When humans play virtual racing games, they use visual environmental information on the game screen to understand the rules within the environments. In contrast, a state-of-the-art realistic racing game AI agent that outperforms human players does not use image-based environ…

Blog

April 4, 2022 | Sony AI

Meet the Team #4: Kenta, Alisa and Thomas

The next installments of our Meet the Team series will feature members of the global Sony AI team who contributed to thegroundbreaking research, Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning, and created…

The next installments of our Meet the Team series will feature members of the global Sony AI team who contributed to thegroundbrea…

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.