Zobrazeno 1 - 10
of 121
pro vyhledávání: '"Uchibe, Eiji"'
Autor:
Yagi, Satoshi, Tada, Mitsunori, Uchibe, Eiji, Kanoga, Suguru, Matsubara, Takamitsu, Morimoto, Jun
This study proposes an approach to human-to-humanoid teleoperation using GAN-based online motion retargeting, which obviates the need for the construction of pairwise datasets to identify the relationship between the human and the humanoid kinematics
Externí odkaz:
http://arxiv.org/abs/2406.00727
Autor:
Wang, Jiexin, Uchibe, Eiji
We introduce the ``soft Deep MaxPain'' (softDMP) algorithm, which integrates the optimization of long-term policy entropy into reward-punishment reinforcement learning objectives. Our motivation is to facilitate a smoother variation of operators util
Externí odkaz:
http://arxiv.org/abs/2405.11784
Autor:
Yamanokuchi, Tomoya, Kwon, Yuhwan, Tsurumine, Yoshihisa, Uchibe, Eiji, Morimoto, Jun, Matsubara, Takamitsu
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:
http://arxiv.org/abs/2207.01840
Autor:
Uchibe, Eiji
Publikováno v:
IEEE Robotics and Automation Letters, Volume 7, Issue 4, pages 10922-10929, October, 2022
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:
http://arxiv.org/abs/2206.10101
The recently successful Munchausen Reinforcement Learning (M-RL) features implicit Kullback-Leibler (KL) regularization by augmenting the reward function with logarithm of the current stochastic policy. Though significant improvement has been shown w
Externí odkaz:
http://arxiv.org/abs/2205.07467
Enforcing KL Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning
Maximum Tsallis entropy (MTE) framework in reinforcement learning has gained popularity recently by virtue of its flexible modeling choices including the widely used Shannon entropy and sparse entropy. However, non-Shannon entropies suffer from appro
Externí odkaz:
http://arxiv.org/abs/2205.07885
Autor:
Asl, Hamed Jabbari, Uchibe, Eiji
Publikováno v:
In Expert Systems With Applications 1 December 2024 255 Part C
Autor:
Asl, Hamed Jabbari, Uchibe, Eiji
Publikováno v:
In Systems & Control Letters November 2024 193
Autor:
Asl, Hamed Jabbari, Uchibe, Eiji
Publikováno v:
In Neural Networks April 2024 172
Autor:
Uchibe, Eiji, Doya, Kenji
Publikováno v:
Neural Networks, December 2021, Pages 138-153
This paper proposes model-free imitation learning named Entropy-Regularized Imitation Learning (ERIL) that minimizes the reverse Kullback-Leibler (KL) divergence. ERIL combines forward and inverse reinforcement learning (RL) under the framework of an
Externí odkaz:
http://arxiv.org/abs/2008.07284