{"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/forward-modeling-for-partial-observation","title":"Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger","arxiv_id":"1812.00054","date":"2018-11-30","proceeding":"ICLR 2018 1","authors":["Gabriel Synnaeve","Zeming Lin","Jonas Gehring","Dan Gant","Vegard Mella","Vasil Khalidov","Nicolas Carion","Nicolas Usunier"],"abstract":"We formulate the problem of defogging as state estimation and future state\nprediction from previous, partial observations in the context of real-time\nstrategy games. We propose to employ encoder-decoder neural networks for this\ntask, and introduce proxy tasks and baselines for evaluation to assess their\nability of capturing basic game rules and high-level dynamics. By combining\nconvolutional neural networks and recurrent networks, we exploit spatial and\nsequential correlations and train well-performing models on a large dataset of\nhuman games of StarCraft: Brood War. Finally, we demonstrate the relevance of\nour models to downstream tasks by applying them for enemy unit prediction in a\nstate-of-the-art, rule-based StarCraft bot. We observe improvements in win\nrates against several strong community bots.","url_abs":"http://arxiv.org/abs/1812.00054v1","url_pdf":"http://arxiv.org/pdf/1812.00054v1.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":"forward-modeling-for-partial-observation","repo_url":"https://github.com/facebookresearch/starcraft_defogger","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"real-time-strategy-games","task_name":"Real-Time Strategy Games"},{"task_slug":"starcraft","task_name":"Starcraft"},{"task_slug":"state-estimation","task_name":"State Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.00054","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}