Výsledky vyhledávání

Akademický článek

Orthogonal Adversarial Deep Reinforcement Learning for Discrete- and Continuous-Action Problems

Autor: Kohei Ohashi, Kosuke Nakanishi, Nao Goto, Yuji Yasui, Shin Ishii

Publikováno v: IEEE Access, Vol 12, Pp 151907-151919 (2024)

Recent advancements in deep neural network (DNN) technology are enhancing the utilities of machine learning and meeting potential demands for real-world applications. Deep reinforcement learning (DRL) is a key component in realizing complex decision-

Externí odkaz: https://doaj.org/article/d9f5c94576194944888428a60a9406e6

Zobrazit plný text záznamu

Akademický článek

Deep Adversarial Reinforcement Learning Method to Generate Control Policies Robust Against Worst-Case Value Predictions

Autor: Kohei Ohashi, Kosuke Nakanishi, Yuji Yasui, Shin Ishii

Publikováno v: IEEE Access, Vol 11, Pp 100798-100809 (2023)

Over the last decade, methods for autonomous control by artificial intelligence have been extensively developed based on deep reinforcement learning (DRL) technologies. However, despite these advances, robustness to noise in observation data remains

Externí odkaz: https://doaj.org/article/f646c54671da448f9ed62a431b72a8f7

Zobrazit plný text záznamu

Akademický článek

Intention estimation and controllable behaviour models for traffic merges

Autor: Aditya Mahajan, Takayasu Kumano, Yuji Yasui

Publikováno v: SICE Journal of Control, Measurement, and System Integration, Vol 14, Iss 2, Pp 59-66 (2021)

This work focuses on decision making for automated driving vehicles in interaction rich scenarios like traffic merges in a flexibly assertive yet safe manner. We propose a Q-learning based approach, that takes in active intention inferences as additi

Externí odkaz: https://doaj.org/article/25f46150964340a6917687fcc408bb90

Zobrazit plný text záznamu

Akademický článek

Deep Adversarial Reinforcement Learning With Noise Compensation by Autoencoder

Autor: Kohei Ohashi, Kosuke Nakanishi, Wataru Sasaki, Yuji Yasui, Shin Ishii

Publikováno v: IEEE Access, Vol 9, Pp 143901-143912 (2021)

We present a new adversarial learning method for deep reinforcement learning (DRL). Based on this method, robust internal representation in a deep Q-network (DQN) was introduced by applying adversarial noise to disturb the DQN policy; however, it was

Externí odkaz: https://doaj.org/article/45f6f2acb3814f7aad2d1ad72c55f884

Zobrazit plný text záznamu

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

Intention estimation and controllable behaviour models for traffic merges

Autor: Yuji Yasui, Takayasu Kumano, Aditya Mahajan

Publikováno v: SICE Journal of Control, Measurement, and System Integration. 14:59-66

This work focuses on decision making for automated driving vehicles in interaction rich scenarios like traffic merges in a flexibly assertive yet safe manner. We propose a Q-learning based approach...

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::921876be7049cbcdc9b174880d87af9b
https://doi.org/10.1080/18824889.2021.1894001

Zobrazit plný text záznamu

Automated Driving in Complex Real-World Scenarios using a Scalable Risk-Based Behavior Generation Framework

Autor: Bram Bolder, Misa Komuro, Benedict Flade, Thomas H. Weisswange, Yosuke Sakamoto, Yuji Yasui, Julian Eggert, Tim Puphal, Malte Probst, Nico Steinhardt, Raphael Wenzel

Publikováno v: ITSC

The task of driving autonomously is difficult due to the vast number of driving situations a system may be facing. Especially higher levels of automation in less restricted scopes remain a topic of active research. In previous work, we introduced a b

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::bff7f5147a54bf368d42a251a757fad6
https://doi.org/10.1109/itsc48978.2021.9564440

Zobrazit plný text záznamu

Akademický článek

Synthesis of a Kinetically Stabilized 2,2-Dihydrosilene.

Autor: Adrie Garcia, Julius, Yuji Yasui, Mariko Yukimoto, Yoshiyuki Mizuhata, Norihiro Tokitoh

Publikováno v: Chemistry Letters; Sep2022, Vol. 51 Issue 9, p898-901, 4p

Zobrazit plný text záznamu

Autonomous Emergency Steering Using Deep Reinforcement Learning For Advanced Driver Assistance System

Autor: Kinsuk Sarkar, Satoru Araki, Abinav Kaushik, Ishaan Sood, Bharat Kumar Padi, Gakuyo Fujimoto, Misako Yoshimura, Amit More, Tsuchiya Masamitsu, Yuji Yasui, Tijmen Tieleman, Abdul Muneer, Matthew Dennison, Anil Hebber

Publikováno v: SICE

Although automobile technology has continuously evolved in recent years, there are still many traffic accidents all over the world. In order to reduce the number of traffic accidents, we focused on developing an emergency collision avoidance system.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4138dc0317df24af5331a8b298fd61b8
https://doi.org/10.23919/sice48898.2020.9240358

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání