niftycent.com
NiftyCent
SK
Prihlásiť sa
Marketplace
Zľavy

Emerging Reasoning with Reinforcement Learning

https://github.com/hkust-nlp/simpleRL-reason

Comments URL: https://news.ycombinator.com/item?id=42827399

Points: 33

# Comments: 5

https://hkust-nlp.notion.site/simplerl-reason

Vytvorené 1mo | 26. 1. 2025, 5:10:07


Ak chcete pridať komentár, prihláste sa

Ostatné príspevky v tejto skupine

Microsoft is reportedly killing Skype after 14 years of neglect
Microsoft is reportedly killing Skype after 14 years of neglect

Article URL: https://www.windowscentral.com/microsoft/microsoft-is-reportedly-kil

28. 2. 2025, 8:10:06 | Hacker news
Show HN: Python micro event loop library (~250 LOC)
Show HN: Python micro event loop library (~250 LOC)

Article URL: https://gist.github.com/tarruda/5b8c19779c8ff4e8100f0b37eb5981ea

Comments URL:

28. 2. 2025, 5:50:13 | Hacker news
Doc NTIA lead nominee criticizes "woke" and "socialist" fiber broadband subsidy
Doc NTIA lead nominee criticizes "woke" and "socialist" fiber broadband subsidy

Article URL: https://broadbandbreakfast.com/incoming-ntia-chief-doesnt-like-bea

28. 2. 2025, 5:50:12 | Hacker news
Putting Andrew Ng's OCR models to the test
Putting Andrew Ng's OCR models to the test

Article URL: https://www.runpulse.com/blog/putting-andrew-ngs-ocr-models-to-the-test

Comments URL:

28. 2. 2025, 5:50:12 | Hacker news
Hydrogen cyanide and acetylene detected in a brown dwarf
Hydrogen cyanide and acetylene detected in a brown dwarf

Article URL: https://phys.org/news/2025-02-hydrogen-cyanide-acetylene-brown-dwarf.html

Comments URL:

28. 2. 2025, 5:50:11 | Hacker news
macOS Tips and Tricks (2022)
macOS Tips and Tricks (2022)

Article URL: https://saurabhs.org/macos-tips

Comments URL: https://news.ycombinator.com

28. 2. 2025, 5:50:09 | Hacker news
US authorities can see more than ever, with Big Tech as their eyes
US authorities can see more than ever, with Big Tech as their eyes

Article URL: https://proton.me/blog/big-tech-data-requests-surge

Comments URL:

28. 2. 2025, 5:50:08 | Hacker news
Techie
Techie