The Effectiveness of World Models for Continual Reinforcement Learning

2 code implementations • 29 Nov 2022 • Samuel Kessler, Mateusz Ostaszewski, Michał Bortkiewicz, Mateusz Żarski, Maciej Wołczyk, Jack Parker-Holder, Stephen J. Roberts, Piotr Miłoś

World models power some of the most efficient reinforcement learning algorithms.

Continual Learning Model-based Reinforcement Learning +2

Computer Vision based inspection on post-earthquake with UAV synthetic dataset

1 code implementation • 11 Oct 2022 • Mateusz Żarski, Bartosz Wójcik, Jarosław A. Miszczak, Bartłomiej Blachowski, Mariusz Ostrowski

The area affected by the earthquake is vast and often difficult to entirely cover, and the earthquake itself is a sudden event that causes multiple defects simultaneously, that cannot be effectively traced using traditional, manual methods.

Hard hat wearing detection based on head keypoint localization

1 code implementation • 21 Jun 2021 • Bartosz Wójcik, Mateusz Żarski, Kamil Książek, Jarosław Adam Miszczak, Mirosław Jan Skibniewski

In recent years, a lot of attention is paid to deep learning methods in the context of vision-based construction site safety systems, especially regarding personal protective equipment.

object-detection Object Detection

KrakN: Transfer Learning framework for thin crack detection in infrastructure maintenance

1 code implementation • 26 Apr 2020 • Mateusz Żarski, Bartosz Wójcik, Jarosław Adam Miszczak

Monitoring the technical condition of infrastructure is a crucial element to its maintenance.

Management Transfer Learning