Zobrazeno 1 - 10 of 91 pro vyhledávání: '"Eiji Uchibe"'
1
Akademický článek
Constrained Deep Q-Learning Gradually Approaching Ordinary Q-Learning
Autor: Shota Ohnishi, Eiji Uchibe, Yotaro Yamaguchi, Kosuke Nakanishi, Yuji Yasui, Shin Ishii
Publikováno v: Frontiers in Neurorobotics, Vol 13 (2019)
A deep Q network (DQN) (Mnih et al., 2013) is an extension of Q learning, which is a typical deep reinforcement learning method. In DQN, a Q function expresses all action values under all states, and it is approximated using a convolutional neural ne
Externí odkaz: https://doaj.org/article/b93b5b7b16874660b7e0bde3e5ef1057
Zobrazit plný text záznamu
2
Akademický článek
Cooperative and Competitive Reinforcement and Imitation Learning for a Mixture of Heterogeneous Learning Modules
Autor: Eiji Uchibe
Publikováno v: Frontiers in Neurorobotics, Vol 12 (2018)
This paper proposes Cooperative and competitive Reinforcement And Imitation Learning (CRAIL) for selecting an appropriate policy from a set of multiple heterogeneous modules and training all of them in parallel. Each learning module has its own netwo
Externí odkaz: https://doaj.org/article/8a243e386a1f4d1186f5d99b097bed95
Zobrazit plný text záznamu
4
Parallel and hierarchical neural mechanisms for adaptive and predictive behavioral control
Autor: Jun Morimoto, Eiji Uchibe, Masayuki Matsumoto, Takatoshi Hikida, Tom Macpherson, Hiroaki Gomi
Publikováno v: Neural Networks. 144:507-521
Our brain can be recognized as a network of largely hierarchically organized neural circuits that operate to control specific functions, but when acting in parallel, enable the performance of complex and simultaneous behaviors. Indeed, many of our da
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ceba473fa619912872d8531ee418b57a
https://doi.org/10.1016/j.neunet.2021.09.009
Zobrazit plný text záznamu
7
Randomized-to-Canonical Model Predictive Control for Real-world Visual Robotic Manipulation
Autor: Tomoya Yamanokuchi, Yuhwan Kwon, Yoshihisa Tsurumine, Eiji Uchibe, Jun Morimoto, Takamitsu Matsubara
Many works have recently explored Sim-to-real transferable visual model predictive control (MPC). However, such works are limited to one-shot transfer, where real-world data must be collected once to perform the sim-to-real transfer, which remains a
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5cce7b81f4cab97d396c001baf6f68a1
http://arxiv.org/abs/2207.01840
Zobrazit plný text záznamu
8
Model-Based Imitation Learning Using Entropy Regularization of Model and Policy
Autor: Eiji Uchibe
Approaches based on generative adversarial networks for imitation learning are promising because they are sample efficient in terms of expert demonstrations. However, training a generator requires many interactions with the actual environment because
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7029ead65a04ba04d46d95aad849a528
http://arxiv.org/abs/2206.10101
Zobrazit plný text záznamu
10
Deep learning, reinforcement learning, and world models
Autor: Yutaka Matsuo, Yann LeCun, Maneesh Sahani, Doina Precup, David Silver, Masashi Sugiyama, Eiji Uchibe, Jun Morimoto
Publikováno v: Neural networks : the official journal of the International Neural Network Society. 152
Deep learning (DL) and reinforcement learning (RL) methods seem to be a part of indispensable factors to achieve human-level or super-human AI systems. On the other hand, both DL and RL have strong connections with our brain functions and with neuros
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::262c4074cdf91df061f3acd6d41e4bce
https://pubmed.ncbi.nlm.nih.gov/35569196
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje