https://hackerpaper.kaipfister.de/p/1705.00154/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=19906900urn:hackerpapers:mention:1705.00154:19906900Tue, 14 May 2019 05:02:10 GMT<p>Author here. IBM is currently focusing on the combination of machine learning and reasoning, also called neural-symbolic AI [1], to combine the best of both worlds (noise robustness and explainability, etc.). I am from Tokyo and will join MIT-IBM lab soon to perform this line of research. I have been working on Latplan [AAAI-2018, 2,3,4,5,6], a neural-symbolic classical planning system that learns symbolic representations of noisy images and perform efficient symbolic planning in the latent space. Later, several other groups have started working in this field, like [7]. The problem with…</p><p><a href="https://hackerpaper.kaipfister.de/p/1705.00154/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AIhttps://news.ycombinator.com/item?id=17660268urn:hackerpapers:mention:1705.00154:17660268Wed, 01 Aug 2018 07:06:50 GMT<p>This approach is very similar to a AAAI18 paper [1] that also finds a binary representation (&quot;plannable representation&quot;) using VAEs and performs planning algorithms, but the difference is that they included some experiments for continuous abstract states. I personally prefer VAEs because GANs are hard to train. [1] arxiv.org/abs/1705.00154</p><p><a href="https://hackerpaper.kaipfister.de/p/1705.00154/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI