A Greedy Approach to Adapting the Trace Parameter for Temporal Difference Learning · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1607.00446/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTA Greedy Approach to Adapting the Trace Parameter for Temporal Difference Learning — mentioned by clickokhttps://news.ycombinator.com/item?id=16778052urn:hackerpapers:mention:1607.00446:16778052Fri, 06 Apr 2018 22:28:53 GMT<p>Yes. In particular, it&#x27;s possible to learn the variance of the return using TD-methods with the same computational complexity as learning the expected value (the value function). See [0] for how to do it via the squared TD-error, or [1] for how to estimate it via the second moment of the return, and my own notes (soon to be published and expanded for my thesis) here [2]. It turns out that identifying states with high variance is a great way of locating model error-- most of the real-world environments are fairly deterministic, so states with high variance tend to be &quot;aliased&quot; combinations of…</p><p><a href="https://hackerpaper.kaipfister.de/p/1607.00446/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI