{"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/planning-in-dynamic-environments-with","title":"Planning in Dynamic Environments with Conditional Autoregressive Models","arxiv_id":"1811.10097","date":"2018-11-25","proceeding":null,"authors":["Johanna Hansen","Kyle Kastner","Aaron Courville","Gregory Dudek"],"abstract":"We demonstrate the use of conditional autoregressive generative models (van\nden Oord et al., 2016a) over a discrete latent space (van den Oord et al.,\n2017b) for forward planning with MCTS. In order to test this method, we\nintroduce a new environment featuring varying difficulty levels, along with\nmoving goals and obstacles. The combination of high-quality frame generation\nand classical planning approaches nearly matches true environment performance\nfor our task, demonstrating the usefulness of this method for model-based\nplanning in dynamic environments.","url_abs":"http://arxiv.org/abs/1811.10097v1","url_pdf":"http://arxiv.org/pdf/1811.10097v1.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":"planning-in-dynamic-environments-with","repo_url":"https://github.com/johannah/trajectories","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}