{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/classical-planning-in-deep-latent-space","title":"Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary","arxiv_id":"1705.00154","date":"2017-04-29","proceeding":null,"authors":["Masataro Asai","Alex Fukunaga"],"abstract":"Current domain-independent, classical planners require symbolic models of the\nproblem domain and instance as input, resulting in a knowledge acquisition\nbottleneck. Meanwhile, although deep learning has achieved significant success\nin many fields, the knowledge is encoded in a subsymbolic representation which\nis incompatible with symbolic systems such as planners. We propose LatPlan, an\nunsupervised architecture combining deep learning and classical planning. Given\nonly an unlabeled set of image pairs showing a subset of transitions allowed in\nthe environment (training inputs), and a pair of images representing the\ninitial and the goal states (planning inputs), LatPlan finds a plan to the goal\nstate in a symbolic latent space and returns a visualized plan execution. The\ncontribution of this paper is twofold: (1) State Autoencoder, which finds a\npropositional state representation of the environment using a Variational\nAutoencoder. It generates a discrete latent vector from the images, based on\nwhich a PDDL model can be constructed and then solved by an off-the-shelf\nplanner. (2) Action Autoencoder / Discriminator, a neural architecture which\njointly finds the action symbols and the implicit action models\n(preconditions/effects), and provides a successor function for the implicit\ngraph search. We evaluate LatPlan using image-based versions of 3 planning\ndomains: 8-puzzle, Towers of Hanoi and LightsOut.","url_abs":"http://arxiv.org/abs/1705.00154v3","url_pdf":"http://arxiv.org/pdf/1705.00154v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"classical-planning-in-deep-latent-space","repo_url":"https://github.com/guicho271828/latplan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.00154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.00154"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guicho271828/latplan","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"685129a16b52e666","entry":"load_blocks","repo":"guicho271828/latplan","repo_kind":"official","path":"latplan/main/blocks.py","file_url":"https://github.com/guicho271828/latplan/blob/HEAD/latplan/main/blocks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"685129a16b52e666"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}