Tootfinder

Expert or not? assessing data quality in offline reinforcement learning
Arip Asadulaev, Fakhri Karray, Martin Takac
https://arxiv.org/abs/2510.12638 https://

Expert or not? assessing data quality in offline reinforcement learning
Offline reinforcement learning (RL) learns exclusively from static datasets, without further interaction with the environment. In practice, such datasets vary widely in quality, often mixing expert, suboptimal, and even random trajectories. The choice of algorithm therefore depends on dataset fidelity. Behavior cloning can suffice on high-quality data, whereas mixed- or low-quality data typically benefits from offline RL methods that stitch useful behavior across trajectories. Yet in the wild i…

heise | Audioplayer für Kinder im Vergleich: Vom Smart Speaker bis zur Offline-Box
Amazon Echo Dot Kids, Galakto Player, Toniebox 2 und Wobie Box buhlen um einen Platz im Kinderzimmer. Die Konzepte könnten kaum unterschiedlicher ausfallen.

Eine Woche offline, zurück in der Realität: Trump sät erneut Hass, Tech-Bosse hofieren ihm devot, die Türkei vergräbt die Demokratie – und die AfD plant mit bürgerlicher Maskierung die Machtergreifung. Währenddessen verändert Apple unbemerkt die Gesellschaft. Zeit für eine #Wochenschau.

Zwischen Hass und Hofierung: Wie Trump, Techkonzerne und Rechtsradikale unsere Demokratie gefährden
Eine Woche offline, zurück in der Realität: Trump sät erneut Hass, Tech-Bosse hofieren ihm devot, die Türkei vergräbt die Demokratie – und die AfD plant mit bürgerlicher Maskierung die Machtergreif…

next #firewalld oddity; you can't use 'firewall-cmd' when firewalld is stopped (like configuring a rootfs not yet booted), but it has got 'firewall-offline-cmd' that lets you do it - except the options are sometimes different; e.g.
firewall-cmd --zone=external --remove-service ssh --permanent
becomes
firewall-offline-cmd --zone=external --remove-service-fro…

Why Are Trump & Joe Rogan So Popular With Young Men? by Offline with Jon Favreau
#masculinity

Store Norske Leksikon skrev at Norsk Syndikalistisk Forbund ble opplŸst i 1973, men heldigvis er de fortsatt her i dag, takk og pris for det, og for at jeg kunne opplyse dem om det!
NSF-IAA på Store Norske Leksikon:
https://snl.no/Norsk_Syndikalistisk_F%C3¸derasjon

Misschien moeten we even een aantal jaartjes alleen vrouwen laten stemmen.
We hebben nog wat goed te maken voor de periode 1917-1922.

Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Data
Jesse van Remmerden, Zaharah Bukhsh, Yingqian Zhang
https://arxiv.org/abs/2509.10303

Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Data
The Job-Shop Scheduling Problem (JSP) and Flexible Job-Shop Scheduling Problem (FJSP), are canonical combinatorial optimization problems with wide-ranging applications in industrial operations. In recent years, many online reinforcement learning (RL) approaches have been proposed to learn constructive heuristics for JSP and FJSP. Although effective, these online RL methods require millions of interactions with simulated environments that may not capture real-world complexities, and their random…

Bundes-Klinik-Atlas geht offline, Verbraucherschützer üben Kritik
Der im Mai 2024 vom Bundesgesundheitsministerium veröffentlichte Klinik-Atlas geht nach nur einem Jahr wieder offline. Die Verbraucherschutzzentrale übt Kritik.

Offline Reinforcement Learning with Generative Trajectory Policies
Xinsong Feng, Leshu Tang, Chenan Wang, Haipeng Chen
https://arxiv.org/abs/2510.11499 https://

Offline Reinforcement Learning with Generative Trajectory Policies
Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex, multi-modal behaviors. However, existing methods face a stark trade-off: slow, iterative models like diffusion policies are computationally expensive, while fast, single-step models like consistency policies often suffer from degraded performance. In this paper, we demonstrate that it is possible to bridge this gap. The key to moving beyond the limitati…