Zobrazeno 1 - 10
of 57
pro vyhledávání: '"Fukuchi, Kazuto"'
This study considers the attack on reinforcement learning agents where the adversary aims to control the victim's behavior as specified by the adversary by adding adversarial modifications to the victim's state observation. While some attack methods
Externí odkaz:
http://arxiv.org/abs/2406.03862
Transfer learning enhances prediction accuracy on a target distribution by leveraging data from a source distribution, demonstrating significant benefits in various applications. This paper introduces a novel dissimilarity measure that utilizes vicin
Externí odkaz:
http://arxiv.org/abs/2405.16906
Deep learning models are susceptible to adversarial attacks, where slight perturbations to input data lead to misclassification. Adversarial attacks become increasingly effective with access to information about the targeted classifier. In the contex
Externí odkaz:
http://arxiv.org/abs/2405.15244
Publikováno v:
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI 2023
A concept-based classifier can explain the decision process of a deep learning model by human-understandable concepts in image classification problems. However, sometimes concept-based explanations may cause false positives, which misregards unrelate
Externí odkaz:
http://arxiv.org/abs/2305.18362
Autor:
Miyagi, Atsuhiro, Miyauchi, Yoshiki, Maki, Atsuo, Fukuchi, Kazuto, Sakuma, Jun, Akimoto, Youhei
In this study, we consider a continuous min--max optimization problem $\min_{x \in \mathbb{X} \max_{y \in \mathbb{Y}}}f(x,y)$ whose objective function is a black-box. We propose a novel approach to minimize the worst-case objective function $F(x) = \
Externí odkaz:
http://arxiv.org/abs/2303.16079
We investigate policy transfer using image-to-semantics translation to mitigate learning difficulties in vision-based robotics control agents. This problem assumes two environments: a simulator environment with semantics, that is, low-dimensional and
Externí odkaz:
http://arxiv.org/abs/2301.13343
In this study, we consider simulation-based worst-case optimization problems with continuous design variables and a finite scenario set. To reduce the number of simulations required and increase the number of restarts for better local optimum solutio
Externí odkaz:
http://arxiv.org/abs/2211.16574
In the field of reinforcement learning, because of the high cost and risk of policy training in the real world, policies are trained in a simulation environment and transferred to the corresponding real-world environment. However, the simulation envi
Externí odkaz:
http://arxiv.org/abs/2211.03413
Evolution strategy (ES) is one of promising classes of algorithms for black-box continuous optimization. Despite its broad successes in applications, theoretical analysis on the speed of its convergence is limited on convex quadratic functions and th
Externí odkaz:
http://arxiv.org/abs/2209.12467
In real-world applications of multi-class classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., speed limit). In this paper, we propose a loss function that can
Externí odkaz:
http://arxiv.org/abs/2209.10920