{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T03:22:36Z","timestamp":1648783356559},"reference-count":0,"publisher":"IOS Press","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,22]]},"abstract":"<jats:p>Symbolic systems require hand-coded symbolic representation as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems. To address the gap between the two fields, one has to solve Symbol Grounding problem: The question of how a machine can generate symbols automatically. We discuss our recent work called Latplan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), Latplan learns a complete propositional PDDL action model of the environment. Later, when a pair of images representing the initial and the goal states (planning inputs) is given, Latplan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution. We discuss several key ideas that made Latplan possible which would hopefully extend to many other symbolic paradigms outside classical planning.<\/jats:p>","DOI":"10.3233\/faia210349","type":"book-chapter","created":{"date-parts":[[2022,1,3]],"date-time":"2022-01-03T10:42:20Z","timestamp":1641206540000},"source":"Crossref","is-referenced-by-count":0,"title":["Chapter 2. Symbolic Reasoning in Latent Space: Classical Planning as an Example"],"prefix":"10.3233","author":[{"given":"Masataro","family":"Asai","sequence":"first","affiliation":[{"name":"MIT-IBM Watson AI Lab, IBM Research Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Kajino","sequence":"additional","affiliation":[{"name":"IBM Research Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Fukunaga","sequence":"additional","affiliation":[{"name":"Graduate School of Arts and Sciences, University of Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Muise","sequence":"additional","affiliation":[{"name":"School of Computing, Queen\u2019s University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","Neuro-Symbolic Artificial Intelligence: The State of the Art"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA210349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,3]],"date-time":"2022-01-03T10:42:20Z","timestamp":1641206540000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA210349"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,22]]},"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia210349","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,22]]}}}