{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T20:39:38Z","timestamp":1762547978732,"version":"build-2065373602"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIIDE"],"abstract":"<jats:p>Procedural Content Generation via Reinforcement Learning (PCGRL) offers a method for training controllable level designer agents without the need for human datasets, using metrics that serve as proxies for level quality as rewards. Existing PCGRL research focuses on single generator agents, but are bottlenecked by the need to frequently recalculate heuristics of level quality and the agent\u2019s need to navigate around potentially large maps. By framing level generation as a multi-agent problem, we mitigate the efficiency bottleneck of single-agent PCGRL by reducing the number of reward calculations relative to the number of agent actions. We also find that multi-agent level generators are better able to generalize to out-of-distribution map shapes, which we argue is due to the generators\u2019 learning more local, modular design policies. We conclude that treating content generation as a distributed, multi-agent task is beneficial for generating functional artifacts at scale.<\/jats:p>","DOI":"10.1609\/aiide.v21i1.36807","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T20:36:07Z","timestamp":1762547767000},"page":"32-42","source":"Crossref","is-referenced-by-count":0,"title":["Video Game Level Design as a Multi-Agent Reinforcement Learning Problem"],"prefix":"10.1609","volume":"21","author":[{"given":"Sam","family":"Earle","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zehua","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eugene","family":"Vinitsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julian","family":"Togelius","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2025,11,7]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIIDE\/article\/download\/36807\/38945","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIIDE\/article\/download\/36807\/38945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T20:36:07Z","timestamp":1762547767000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIIDE\/article\/view\/36807"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,7]]},"references-count":0,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,11,7]]}},"URL":"https:\/\/doi.org\/10.1609\/aiide.v21i1.36807","relation":{},"ISSN":["2334-0924","2326-909X"],"issn-type":[{"value":"2334-0924","type":"electronic"},{"value":"2326-909X","type":"print"}],"subject":[],"published":{"date-parts":[[2025,11,7]]}}}