{"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/qmdp-net-deep-learning-for-planning-under","title":"QMDP-Net: Deep Learning for Planning under Partial Observability","arxiv_id":"1703.06692","date":"2017-03-20","proceeding":"NeurIPS 2017 12","authors":["Peter Karkus","David Hsu","Wee Sun Lee"],"abstract":"This paper introduces the QMDP-net, a neural network architecture for\nplanning under partial observability. The QMDP-net combines the strengths of\nmodel-free learning and model-based planning. It is a recurrent policy network,\nbut it represents a policy for a parameterized set of tasks by connecting a\nmodel with a planning algorithm that solves the model, thus embedding the\nsolution structure of planning in a network learning architecture. The QMDP-net\nis fully differentiable and allows for end-to-end training. We train a QMDP-net\non different tasks so that it can generalize to new ones in the parameterized\ntask set and \"transfer\" to other similar tasks beyond the set. In preliminary\nexperiments, QMDP-net showed strong performance on several robotic tasks in\nsimulation. Interestingly, while QMDP-net encodes the QMDP algorithm, it\nsometimes outperforms the QMDP algorithm in the experiments, as a result of\nend-to-end learning.","url_abs":"http://arxiv.org/abs/1703.06692v3","url_pdf":"http://arxiv.org/pdf/1703.06692v3.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":"qmdp-net-deep-learning-for-planning-under","repo_url":"https://github.com/AdaCompNUS/qmdp-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"qmdp-net-deep-learning-for-planning-under","repo_url":"https://github.com/kage08/qmdp-net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1703.06692","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}