Spremljaj
Akifumi Wachi
Akifumi Wachi
Chief Research Scientist, LY Corporation
Preverjeni e-poštni naslov na lycorp.co.jp - Domača stran
Naslov
Navedeno
Navedeno
Leto
Safe Reinforcement Learning in Constrained Markov Decision Processes
A Wachi, Y Sui
International Conference on Machine Learning (ICML), 2020
2042020
Safe Exploration and Optimization of Constrained MDPs Using Gaussian Processes.
A Wachi, Y Sui, Y Yue, M Ono
AAAI Conference on Artificial Intelligence (AAAI), 6548-6556, 2018
1632018
Failure-scenario maker for rule-based agent using multi-agent adversarial reinforcement learning and its application to autonomous driving
A Wachi
International Joint Conference on Artificial Intelligence (IJCAI), 6006-6012, 2019
732019
Verbosity bias in preference labeling by large language models
K Saito, A Wachi, K Wataoka, Y Akimoto
arXiv preprint arXiv:2310.10076, 2023
532023
Neuro-symbolic reinforcement learning with first-order logic
D Kimura, M Ono, S Chaudhury, R Kohita, A Wachi, DJ Agravante, ...
arXiv preprint arXiv:2110.10963, 2021
482021
Reinforcement learning with external knowledge by using logical neural networks
D Kimura, S Chaudhury, A Wachi, R Kohita, A Munawar, M Tatsubori, ...
arXiv preprint arXiv:2103.02363, 2021
162021
Safe policy optimization with local generalized linear function approximations
A Wachi, Y Wei, Y Sui
Advances in Neural Information Processing Systems 34, 20759-20771, 2021
142021
A Survey of Constraint Formulations in Safe Reinforcement Learning
A Wachi, X Shen, Y Sui
IJCAI-24 / arXiv preprint arXiv:2402.02025, 2024
132024
Integral design method for simple and small Mars lander system using membrane aeroshell
R Sakagami, R Takahashi, A Wachi, Y Koshiro, H Maezawa, Y Kasai, ...
Acta Astronautica 144, 103-118, 2018
132018
Safe exploration in reinforcement learning: A generalized formulation and algorithms
A Wachi, W Hashimoto, X Shen, K Hashimoto
Advances in Neural Information Processing Systems 36, 29252-29272, 2023
112023
LOA: Logical optimal actions for text-based interaction games
D Kimura, S Chaudhury, M Ono, M Tatsubori, DJ Agravante, A Munawar, ...
arXiv preprint arXiv:2110.10973, 2021
112021
Mars entry, descent, and landing by small THz spacecraft via membrane aeroshell
A Wachi, R Takahashi, R Sakagami, Y Koshiro, Y Kasai, S Nakasuka
AIAA SPACE and Astronautics Forum and Exposition, 5313, 2017
72017
Learning-based Event-triggered MPC with Gaussian processes under terminal constraints
Y Onoue, K Hashimoto, A Wachi
arXiv preprint arXiv:2110.12214, 2021
52021
Language-based general action template for reinforcement learning agents
R Kohita, A Wachi, D Kimura, S Chaudhury, M Tatsubori, A Munawar
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 …, 2021
52021
Safe exploration in Markov decision processes with time-variant safety using spatio-temporal gaussian process
A Wachi, H Kajino, A Munawar
arXiv preprint arXiv:1809.04232, 2018
52018
Stepwise alignment for constrained language model policy optimization
A Wachi, T Tran, R Sato, T Tanabe, Y Akimoto
Advances in Neural Information Processing Systems 37, 104471-104520, 2024
42024
Polar embedding
R Iwamoto, R Kohita, A Wachi
Proceedings of the 25th Conference on Computational Natural Language …, 2021
42021
The conceptual design of a novel, small and simple Mars lander
R Takahashi, R Sakagami, A Wachi, Y Kasai, S Nakasuka
IEEE Aerospace Conference, 1-10, 2018
42018
Long-term Safe Reinforcement Learning with Binary Feedback
A Wachi, W Hashimoto, K Hashimoto
AAAI-24 / arXiv preprint arXiv:2401.03786, 2024
32024
Adversarial input generation using variational autoencoder
A Wachi
US Patent 11,715,016, 2023
32023
Sistem trenutno ne more izvesti postopka. Poskusite znova pozneje.
Članki 1–20