{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T13:26:04Z","timestamp":1777728364599,"version":"3.51.4"},"reference-count":31,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T00:00:00Z","timestamp":1716940800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Intelligenza Artificiale: The international journal of the AIxIA"],"published-print":{"date-parts":[[2024,10,9]]},"abstract":"<jats:p>In the last few decades we have witnessed a significant development in Artificial Intelligence (AI) thanks to the availability of a variety of testbeds, mostly based on simulated environments and video games. Among those, roguelike games offer a very good trade-off in terms of complexity of the environment and computational costs, which makes them perfectly suited to test AI agents generalization capabilities. In this work, we present LuckyMera, a flexible, modular, extensible and configurable AI framework built around NetHack, a popular terminal-based, single-player roguelike video game. This library is aimed at simplifying and speeding up the development of AI agents capable of successfully playing the game and offering a high-level interface for designing game strategies. LuckyMera comes with a set of off-the-shelf symbolic and neural modules (called \"skills\"): these modules can be either hard-coded behaviors, or neural Reinforcement Learning approaches, with the possibility of creating compositional hybrid solutions. Additionally, LuckyMera comes with a set of utility features to save its experiences in the form of trajectories for further analysis and to use them as datasets to train neural modules, with a direct interface to the NetHack Learning Environment and MiniHack. Through an empirical evaluation we validate our skills implementation and propose a strong baseline agent that can reach state-of-the-art performances in the complete NetHack game. LuckyMera is open-source and available at https:\/\/github.com\/Pervasive-AI-Lab\/LuckyMera .<\/jats:p>","DOI":"10.3233\/ia-230034","type":"journal-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T10:54:32Z","timestamp":1717152872000},"page":"191-203","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["LuckyMera: a modular AI framework for building hybrid NetHack agents"],"prefix":"10.1177","volume":"18","author":[{"given":"Luigi","family":"Quarantiello","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Pisa, Pisa, Italy"}]},{"given":"Simone","family":"Marzeddu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Pisa, Pisa, Italy"}]},{"given":"Antonio","family":"Guzzi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Pisa, Pisa, Italy"}]},{"given":"Vincenzo","family":"Lomonaco","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Pisa, Pisa, Italy"}]}],"member":"179","published-online":{"date-parts":[[2024,5,29]]},"reference":[{"key":"ref001","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref002","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref003","author":"Berner C.","year":"2019","journal-title":"arXivpreprint arXiv:1912.06680"},{"key":"ref004","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v2i1.18740"},{"key":"ref005","unstructured":"BrockmanG., CheungV., PetterssonL., SchneiderJ., SchulmanJ., TangJ., ZarembaW., Openai gym, 2016."},{"key":"ref006","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v13i1.12923"},{"key":"ref007","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2861759"},{"key":"ref008","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2861759"},{"key":"ref009","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00129-1"},{"key":"ref010","author":"Chester A.","year":"2023","journal-title":"Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2022"},{"key":"ref011","doi-asserted-by":"crossref","unstructured":"DijkstraE.W., A note on two problems in connexion with graphs. In Edsger Wybe Dijkstra: His Life, Work, and Legacy, (2022), pp. 287\u2013290. Numerische Mathematik.","DOI":"10.1145\/3544585.3544600"},{"key":"ref012","author":"Espeholt L.","journal-title":"International Conference on Machine Learning"},{"key":"ref013","author":"Farag W.","year":"2018","journal-title":"2018 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT)"},{"key":"ref014","doi-asserted-by":"publisher","DOI":"10.5334\/jors.444"},{"key":"ref015","author":"Hambro E.","year":"2022","journal-title":"NeurIPS 2021 Competitions and Demonstrations Track"},{"key":"ref016","author":"Hambro E.","year":"2022","journal-title":"arXiv preprint arXiv:2211.00539"},{"key":"ref017","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref018","author":"Henaff M.","year":"2022","journal-title":"arXiv preprint arXiv:2210.05805"},{"key":"ref019","author":"Kessler S.","year":"2022","journal-title":"arXiv preprint arXiv:2211.15944"},{"key":"ref020","author":"Kuttler H.","year":"2019","journal-title":"arXiv preprint arXiv:1910.03552"},{"key":"ref021","first-page":"7671","volume":"33","author":"Kuttler H.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref022","author":"Lanctot M.","year":"2019","journal-title":"arXiv preprint arXiv:1908.09453"},{"key":"ref023","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref024","author":"Mnih V.","year":"2013","journal-title":"arXiv preprint arXiv:1312.5602"},{"key":"ref025","author":"Powers S.","year":"2022","journal-title":"Conference on Lifelong Learning Agents"},{"key":"ref026","author":"Ross S.","year":"2011","journal-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics"},{"key":"ref027","author":"Samvelyan M.","year":"2021","journal-title":"arXiv preprint arXiv:2109.13202"},{"key":"ref028","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref029","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref030","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref031","first-page":"1","author":"Zheng B.","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"}],"container-title":["Intelligenza Artificiale: The international journal of the AIxIA"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/IA-230034","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/IA-230034","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/IA-230034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:51:53Z","timestamp":1777459913000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/IA-230034"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,29]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,10,9]]}},"alternative-id":["10.3233\/IA-230034"],"URL":"https:\/\/doi.org\/10.3233\/ia-230034","relation":{},"ISSN":["1724-8035","2211-0097"],"issn-type":[{"value":"1724-8035","type":"print"},{"value":"2211-0097","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,29]]}}}