no code implementations • 30 Jan 2024 • Ryoma Furuyama, Daiki Kuyoshi, Satoshi Yamane
In order to make this algorithm more robust to distribution shift, we propose more efficient and robust algorithm by adding to this method a reward function based on adversarial inverse reinforcement learning that rewards the agent for performing actions in status similar to the demo.
no code implementations • 15 Oct 2023 • Dianbo Ma, Jianqiang Xiao, Ziyan Gao, Satoshi Yamane
In this work, we propose a novel staged depthwise correlation and feature fusion network, named DCFFNet, to further optimize the feature extraction for visual tracking.
1 code implementation • 19 Jan 2020 • Daichi Nishio, Daiki Kuyoshi, Toi Tsuneda, Satoshi Yamane
The methods based on reinforcement learning, such as inverse reinforcement learning and generative adversarial imitation learning (GAIL), can learn from only a few expert data.
no code implementations • 21 May 2019 • Kazuki Takamura, Satoshi Yamane
As a result of the experiment, the effectiveness of the proposed method was confirmed.
1 code implementation • 3 Apr 2019 • Daichi Nishio, Satoshi Yamane
End-to-end deep reinforcement learning has enabled agents to learn with little preprocessing by humans.
no code implementations • 30 Mar 2019 • Tetsuto Takano, Satoshi Yamane
The paper propose a new model which can integrate context information and make translation.
no code implementations • 6 Jan 2018 • Daichi Nishio, Satoshi Yamane
The research on deep reinforcement learning which estimates Q-value by deep learning has been attracted the interest of researchers recently.