{"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/adaptive-path-integral-autoencoder","title":"Adaptive Path-Integral Autoencoder: Representation Learning and Planning for Dynamical Systems","arxiv_id":"1807.02128","date":"2018-07-05","proceeding":null,"authors":["Jung-Su Ha","Young-Jin Park","Hyeok-Joo Chae","Soon-Seo Park","Han-Lim Choi"],"abstract":"We present a representation learning algorithm that learns a low-dimensional\nlatent dynamical system from high-dimensional \\textit{sequential} raw data,\ne.g., video. The framework builds upon recent advances in amortized inference\nmethods that use both an inference network and a refinement procedure to output\nsamples from a variational distribution given an observation sequence, and\ntakes advantage of the duality between control and inference to approximately\nsolve the intractable inference problem using the path integral control\napproach. The learned dynamical model can be used to predict and plan the\nfuture states; we also present the efficient planning method that exploits the\nlearned low-dimensional latent dynamics. Numerical experiments show that the\nproposed path-integral control based variational inference method leads to\ntighter lower bounds in statistical model learning of sequential data. The\nsupplementary video: https://youtu.be/xCp35crUoLQ","url_abs":"http://arxiv.org/abs/1807.02128v4","url_pdf":"http://arxiv.org/pdf/1807.02128v4.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":"adaptive-path-integral-autoencoder","repo_url":"https://github.com/yjparkLiCS/18-NIPS-APIAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"adaptive-path-integral-autoencoder","repo_url":"https://github.com/yjparkLiCS/18-NeurIPS-APIAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.02128","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}