PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2509.19128/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTPipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation — mentioned by muchomuchach0https://news.ycombinator.com/item?id=46900848urn:hackerpapers:mention:2509.19128:46900848Thu, 05 Feb 2026 15:39:33 GMT<p>https://arxiv.org/abs/2509.19128</p><p><a href="https://hackerpaper.kaipfister.de/p/2509.19128/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG