https://hackerpaper.kaipfister.de/p/1705.02955/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=15983339urn:hackerpapers:mention:1705.02955:15983339Thu, 21 Dec 2017 22:14:48 GMT<p>One of the researchers on this team gave a great talk at NIPS this year about this work and explained how playing an imperfect information game like poker is fundamentally different from playing a perfect information game like chess or go. A perfect information game has no path dependence --- once you arrive at a state, it doesn&#x27;t matter how you got there. You only need to consider the current state of the game to figure out the best move to play. In an imperfect information game this is no longer true. Now you need to consider counterfactuals --- how would the opponent have played if I had…</p><p><a href="https://hackerpaper.kaipfister.de/p/1705.02955/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AIhttps://news.ycombinator.com/item?id=15897632urn:hackerpapers:submission:1705.02955:15897632Mon, 11 Dec 2017 15:35:32 GMT<p>Safe and Nested Subgame Solving for Imperfect-Information Games [pdf]</p><p></p><p>2 points; 1 discussion reply on HN. <a href="https://hackerpaper.kaipfister.de/p/1705.02955/">Paper and source history</a>. A submission is not an endorsement.</p>cs.AI