Zobrazeno 1 - 10
of 93
pro vyhledávání: '"Matsunaga, Daiki"'
Publikováno v:
EMNLP 2024
A critical component of the current generation of language models is preference alignment, which aims to precisely control the model's behavior to meet human needs and values. The most notable among such methods is Reinforcement Learning with Human F
Externí odkaz:
http://arxiv.org/abs/2410.15096
Offline Goal-Conditioned Reinforcement Learning (Offline GCRL) is an important problem in RL that focuses on acquiring diverse goal-oriented skills solely from pre-collected behavior datasets. In this setting, the reward feedback is typically absent
Externí odkaz:
http://arxiv.org/abs/2402.07226
Autor:
Matsunaga, Daiki E., Lee, Jongmin, Yoon, Jaeseok, Leonardos, Stefanos, Abbeel, Pieter, Kim, Kee-Eung
One of the main challenges in offline Reinforcement Learning (RL) is the distribution shift that arises from the learned policy deviating from the data collection policy. This is often addressed by avoiding out-of-distribution (OOD) actions during po
Externí odkaz:
http://arxiv.org/abs/2311.02194
Autor:
Zöttl, Andreas, Tesser, Francesca, Matsunaga, Daiki, Laurent, Justine, Roure, Olivia Du, Lindner, Anke
The migration of helical particles in viscous shear flows plays a crucial role in chiral particle sorting. Attaching a non-chiral head to a helical particle leads to a rheotactic torque inducing particle reorientation. This phenomenon is responsible
Externí odkaz:
http://arxiv.org/abs/2211.09213
We investigate how ferrofluid droplets suspended in a wall-bounded shear flow can organise when subjected to an external magnetic field. By tuning the magnitude of the external magnetic field, we find that the ferrofluid droplets form chain-like stru
Externí odkaz:
http://arxiv.org/abs/2112.13362
Autor:
Li, Honghan, Matsunaga, Daiki, Matsui, Tsubasa S., Aosaki, Hiroki, Inoue, Koki, Doostmohammadi, Amin, Deguchi, Shinji
Combining experiments with artificial intelligence algorithms, we propose a new machine learning based approach to extract the cellular force distributions from the microscope images. The full process can be divided into three steps. First, we cultur
Externí odkaz:
http://arxiv.org/abs/2102.12069
Publikováno v:
Phys. Rev. Lett. 126, 078001 (2021)
We study an active matter system comprised of magnetic microswimmers confined in a microfluidic channel and show that it exhibits a new type of self-organized behavior. Combining analytical techniques and Brownian dynamics simulations, we demonstrate
Externí odkaz:
http://arxiv.org/abs/2010.02853
We investigate the collective motion of magnetic rotors suspended in a viscous fluid under an uniform rotating magnetic field. The rotors are positioned on a square lattice, and low Reynolds hydrodynamics is assumed. For a $3 \times 3$ array of magne
Externí odkaz:
http://arxiv.org/abs/2003.05082
Recently, there has been a surge of interest in the use of machine learning to help aid in the accurate predictions of financial markets. Despite the exciting advances in this cross-section of finance and AI, many of the current approaches are limite
Externí odkaz:
http://arxiv.org/abs/1909.10660
We propose an image-based cellular contractile force evaluation method using a machine learning technique. We use a special substrate that exhibits wrinkles when cells grab the substrate and contract, and the wrinkles can be used to visualize the for
Externí odkaz:
http://arxiv.org/abs/1908.08631