Genetic Algorithms for Evolving Computer Chess Programs · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1711.08337/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTGenetic Algorithms for Evolving Computer Chess Programs — mentioned by measurablefunchttps://news.ycombinator.com/item?id=45840462urn:hackerpapers:mention:1711.08337:45840462Thu, 06 Nov 2025 21:11:02 GMT<p>It can and it does work w/ such objective functions. Lots of people have used evolutionary algorithms to evolve chess playing neural networks¹ &amp; they have been successful w/ very sparse reward signals where the the final trajectory is scored w/ 0 or 1 according to a win condition. You can say this is not likely to work for proof search &amp; I&#x27;d be inclined to agree but the strategy has proven to work in simpler settings so whether it can be used in more complex settings is yet to be determined. If Collatz is not independent of existing axiomatic foundations then a brute force search will find a…</p><p><a href="https://hackerpaper.kaipfister.de/p/1711.08337/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.NE