Reward-Conditioned Policies · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1912.13465/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTReward-Conditioned Policies — mentioned by tastroderhttps://news.ycombinator.com/item?id=24773918urn:hackerpapers:mention:1912.13465:24773918Wed, 14 Oct 2020 07:00:21 GMT<p>They mention Rainbow in the related work section of the third paper listed there, Kumar, A., Peng, X. B., &amp; Levine, S. (2019). Reward-Conditioned Policies. arXiv:1912.13465 as part of this remark: &quot;they are also known to be notoriously challenging to use effectively, due to sensitivity to hyper parameters, high sample complexity, and a range of important and delicate implementation choices that have a large effect on performance [5, 6, 12, 15, 23, 24, 46].&quot;</p><p><a href="https://hackerpaper.kaipfister.de/p/1912.13465/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG