News for hackers. Stuff that matters.
Re:Q-learning is not yet scalable by s-mon on Saturday June 14, 2025 @11:34PM (#44280343)
While I like the blogpost, I think the use of unexplained acronyms undermines the opportunity of this blogpost to be useful to the wider audience. Small nit: make sure acronyms and jargon is explained.
Re:Q-learning is not yet scalable by keremk on Sunday June 15, 2025 @07:10AM (#44281691)
For these kinds of blogposts where the content is very good but not very approachable due to assumption of extensive prior knowledge, I find using an AI tool very useful, to explain and simplify. Just used the new browser Dia for this, and it worked really well for me. Or you can use your favorite model provider and copy and paste. This way the post stays concise, and yet you can use your AI tools to ask questions and clarify.
Re:Q-learning is not yet scalable by anonthrowawy on Sunday June 15, 2025 @09:48AM (#44282283)
i actually think thats what made it crisp
Re:Q-learning is not yet scalable by levocardia on Sunday June 15, 2025 @11:57AM (#44282968)
It's clearly written for an audience of other RL researchers, given than the conclusion is "will someone please come up with Q-learning methods that scale!"