{"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/addressing-the-fundamental-tension-of-pcgml","title":"Addressing the Fundamental Tension of PCGML with Discriminative Learning","arxiv_id":"1809.04432","date":"2018-09-10","proceeding":null,"authors":["Isaac Karth","Adam M. Smith"],"abstract":"Procedural content generation via machine learning (PCGML) is typically\nframed as the task of fitting a generative model to full-scale examples of a\ndesired content distribution. This approach presents a fundamental tension: the\nmore design effort expended to produce detailed training examples for shaping a\ngenerator, the lower the return on investment from applying PCGML in the first\nplace. In response, we propose the use of discriminative models (which capture\nthe validity of a design rather the distribution of the content) trained on\npositive and negative examples. Through a modest modification of\nWaveFunctionCollapse, a commercially-adopted PCG approach that we characterize\nas using elementary machine learning, we demonstrate a new mode of control for\nlearning-based generators. We demonstrate how an artist might craft a focused\nset of additional positive and negative examples by critique of the generator's\nprevious outputs. This interaction mode bridges PCGML with mixed-initiative\ndesign assistance tools by working with a machine to define a space of valid\ndesigns rather than just one new design.","url_abs":"http://arxiv.org/abs/1809.04432v1","url_pdf":"http://arxiv.org/pdf/1809.04432v1.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":"addressing-the-fundamental-tension-of-pcgml","repo_url":"https://github.com/mxgmn/WaveFunctionCollapse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}