Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1912.02875/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTReinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions — HN submissionhttps://news.ycombinator.com/item?id=21747094urn:hackerpapers:submission:1912.02875:21747094Mon, 09 Dec 2019 22:00:45 GMT<p>Reinforcement Learning Upside Down: Don&#x27;t Predict Rewards, Map to Actions</p><p></p><p>12 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/1912.02875/">Paper and source history</a>. A submission is not an endorsement.</p>cs.AI