Takuma
Seno
Profile
Takuma joined Sony AI in Oct 2020 as a machine learning engineer, following part-time research positions at Sony R&D Center, Ghelia and Okinawa Institute of Science and Technology. He received his master’s degree in computer science at Keio University in 2019, and is currently pursuing his Ph.D. Takuma’s main research interest is deep reinforcement learning. He developed an offline deep reinforcement learning library, d3rlpy, funded by the IPA MITOU program in 2020, and was certified as a MITOU Super Creator in 2021.
Message
“I am currently working with the Game AI flagship project where we are tackling many practical and theoretical reinforcement learning challenges. There are an enormous number of potential projects where we can leverage the power of reinforcement learning at Sony, and I'm very excited to see what we can do for Sony and the future.”
Publications
In model-based reinforcement learning (MBRL), policy gradients can be estimated either by derivative-free RL methods, such as likelihood ratio gradients (LR), or by backpropagating through a differentiable model via reparameterization gradients (RP). Instead of using one or …
While existing automatic differentiation (AD) frameworks allow flexibly composing model architectures, they do not provide the same flexibility for composing learning algorithms---everything has to be implemented in terms of back propagation. To address this gap, we invent A…
Designing reinforcement learning (RL) agents is typically a difficult process that requires numerous design iterations. Learning can fail for a multitude of reasons and standard RL methods provide too few tools to provide insight into the exact cause. In this paper, we show …
In this paper, we introduce d3rlpy, an open-sourced offline deep reinforcement learning (RL) library for Python. d3rlpy supports a set of offline deep RL algorithms as well as off-policy online algorithms via a fully documented plug-and-play API. To address a reproducibility…
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…
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…
In this paper, we introduce d3rlpy, an open-sourced offline deep reinforcement learning (RL) library for Python. d3rlpy supports a number of offline deep RL algorithms as well as online algorithms via a user-friendly API. To assist deep RL research and development projects, …
Blog
November 1, 2022 | Sony AI
Meet the Team #6: Florian Fuchs, Takuma Seno, Yunshu Du
The sixth installment of our Meet the Team series features members of the global Sony AI team who contributed to the groundbreaking research, Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning, and create…
The sixth installment of our Meet the Team series features members of the global Sony AI team who contributed to the groundbreaki…
June 14, 2022 | Gaming | GT Sophy
Training the World’s Fastest Gran Turismo Racer
GT SOPHY TECHNICAL SERIES Starting in 2020, the research and engineering team at Sony AI set out to do something that had never been done before: create an AI agent that could beat the best drivers in the world at the PlayStation®…
GT SOPHY TECHNICAL SERIES Starting in 2020, the research and engineering team at Sony AI set out to do something that had never be…
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.
