https://hackerpaper.kaipfister.de/p/2410.05364/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=48884042urn:hackerpapers:mention:2410.05364:48884042Sun, 12 Jul 2026 19:48:43 GMT<p>Ha, interesting. I wasn&#x27;t aware of Sutton&#x27;s blog post, but if I might make a shameless plug, we demonstrated [1] exactly this problem (see section 4.4.3), and how multi-step world models (using diffusion models as the substrate) could be one potential answer. Since then, I have come to like temporally-abstract models more and more. Rolling out in time -- either step-by-step or many steps at once -- suffers from the tyranny of the specific. For long horizon planning with agents, I care (often only approximately) about where I can end up, and seldom about exactly when I end up there. Successor…</p><p><a href="https://hackerpaper.kaipfister.de/p/2410.05364/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG