Follow
Takuma Seno
Takuma Seno
Sony AI
Verified email at sony.com - Homepage
Title
Cited by
Cited by
Year
Outracing champion Gran Turismo drivers with deep reinforcement learning
PR Wurman, S Barrett, K Kawamoto, J MacGlashan, K Subramanian, ...
Nature 602 (7896), 223-228, 2022
4382022
d3rlpy: An Offline Deep Reinforcement Learning Library
T Seno, M Imai
Journal of Machine Learning Research 23 (315), 1-20, 2022
1642022
Value Function Decomposition for Iterative Design of Reinforcement Learning Agents
J MacGlashan, E Archer, A Devlic, T Seno, C Sherstan, PR Wurman, ...
Advances in Neural Information Processing Systems 36, 2022
92022
Model-based Reinforcement Learning with Scalable Composite Policy Gradient Estimators
P Parmas, T Seno, Y Aoki
Proceedings of the 40th International Conference on Machine Learning, 27346 …, 2023
62023
Accumulator based arbitration model for both supervised and reinforcement learning inspired by prefrontal cortex
M Osawa, Y Ashihara, T Seno, M Imai, S Kurihara
Neural Information Processing: 24th International Conference, ICONIP 2017 …, 2017
62017
Adaptive semi-autonomous agents via episodic control
T Seno, K Okuoka, M Osawa, M Imai
Proceedings of the 6th International Conference on Human-Agent Interaction …, 2018
52018
Expert Human-Level Driving in Gran Turismo Sport Using Deep Reinforcement Learning with Image-based Representation
R Imamura, T Seno, K Kawamoto, M Spranger
NeurIPS Deep Reinforcement Learning Workshop, 2021
32021
Proppo: a Message Passing Framework for Customizable and Composable Learning Algorithms
P Parmas, T Seno
Advances in Neural Information Processing Systems 36, 2022
22022
予測的認知と 「間」 の関係ーー言葉を話せないロボットによるしりとりを題材とした考察
大藤聖菜, 妹尾卓磨, 清丸寛一, 川崎邦将, 大澤正彦, 長田茂美, ...
HAI シンポジウム 2017, 2017
22017
A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismo
M Vasco, T Seno, K Kawamoto, K Subramanian, PR Wurman, P Stone
arXiv preprint arXiv:2406.12563, 2024
12024
Policy gradients with memory-augmented critic: Stabilizing off-policy policy gradients via differentiable memory
T Seno, M Imai
Transactions of the Japanese Society for Artificial Intelligence 36 (1), 1-8, 2021
12021
An Intrinsically Motivated Robot Explores Non-reward Environments with Output Arbitration
T Seno, M Osawa, M Imai
Biologically Inspired Cognitive Architectures 2018: Proceedings of the Ninth …, 2019
12019
Tunable agent behaviors through continuous reward weight-based goal spaces
F Fuchs, C Sherstan, T Seno, DU Yunshu, P MacAlpine, A Devlic, ...
US Patent App. 18/313,871, 2024
2024
SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning
H Lee, D Hwang, D Kim, H Kim, JJ Tai, K Subramanian, PR Wurman, ...
arXiv preprint arXiv:2410.09754, 2024
2024
高精度レーシングシミュレータへの深層強化学習の応用: Gran Turismo Sophy™
妹尾卓磨, 河本献太
人工知能 38 (5), 628-636, 2023
2023
Artificial intelligence for driving lines in racing games
P Wurman, K Subramanian, F Fuchs, T Seno, K Kawamoto
US Patent App. 17/650,300, 2023
2023
A Study on Designing a Deep Reinforcement Learning Library towards Practical Applications
T Seno
Keio University, 2023
2023
画像キャプションに対する表現学習に向けた敵対的生成ネットワーク
阿部佑樹, 妹尾卓磨, 松森匠哉, 今井倫太
人工知能学会全国大会論文集 第 33 回 (2019), 3Rin230-3Rin230, 2019
2019
会議報告 2018 the Joint Multi-Conference on Human-Level Artificial Intelligence (HLAI 2018)
松森匠哉, 妹尾卓磨, 大澤正彦, 山川宏
人工知能 33 (6), 911-912, 2018
2018
深層強化学習によるロボットの無報酬な環境の探索
妹尾卓磨, 大澤正彦, 今井倫太
第 80 回全国大会講演論文集 2018 (1), 223-224, 2018
2018
The system can't perform the operation now. Try again later.
Articles 1–20