{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:29:34Z","timestamp":1757622574428,"version":"3.44.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032007995"},{"type":"electronic","value":"9783032008008"}],"license":[{"start":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T00:00:00Z","timestamp":1754524800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T00:00:00Z","timestamp":1754524800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-00800-8_18","type":"book-chapter","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T06:56:47Z","timestamp":1754463407000},"page":"202-213","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["From Thought to\u00a0Action: Bridging Cognitive Processes and\u00a0Autonomous MORL Towards Intelligent Agents in\u00a0a\u00a0Virtual Environment"],"prefix":"10.1007","author":[{"given":"Shagofta","family":"Shabashkhan","sequence":"first","affiliation":[]},{"given":"Xiaoyang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"C\u00e9dric S.","family":"Mesnage","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,7]]},"reference":[{"key":"18_CR1","unstructured":"Bakker, P.B.: The state of mind reinforcement learning with recurrent neural networks. Phd thesis (2004)"},{"issue":"4","key":"18_CR2","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1023\/A:1025696116075","volume":"13","author":"AG Barto","year":"2003","unstructured":"Barto, A.G., Mahadevan, S.: Recent advances in hierarchical reinforcement learning. Disc. Event Dyn. Syst. 13(4), 341\u2013379 (2003). https:\/\/doi.org\/10.1023\/A:1025696116075","journal-title":"Disc. Event Dyn. Syst."},{"key":"18_CR3","unstructured":"Bellman, R.: Dynamic Programming. Dover Publications (1957)"},{"key":"18_CR4","unstructured":"Burda, Y., Edwards, H., Pathak, D., Storkey, A., Darrell, T., Efros, A.A.: Large-scale study of curiosity-driven learning. arXiv preprint arXiv:1808.04355 (2018)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"(FAIR) , M.F.A.R.D.T., et\u00a0al.: Human-level play in the game of diplomacy by combining language models with strategic reasoning. Science 378(6624), 1067\u20131074 (2022)","DOI":"10.1126\/science.ade9097"},{"key":"18_CR6","unstructured":"Feng, T., et\u00a0al.: How far are we from AGI (2024). https:\/\/arxiv.org\/abs\/2405.10313"},{"issue":"1","key":"18_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10458-022-09552-y","volume":"36","author":"CF Hayes","year":"2022","unstructured":"Hayes, C.F., R\u0103dulescu, R., Bargiacchi, E., K\u00e4llstr\u00f6m, J., Macfarlane, M., Reymond, M., Verstraeten, T., Zintgraf, L.M., Dazeley, R., Heintz, F., Howley, E., Irissappane, A.A., Mannion, P., Now\u00e9, A., Ramos, G., Restelli, M., Vamplew, P., Roijers, D.M.: A practical guide to multi-objective reinforcement learning and planning. Autonomous Agents and Multi-Agent Systems 36(1), 1\u201359 (2022). https:\/\/doi.org\/10.1007\/s10458-022-09552-y","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Hern\u00e1ndez-Orallo, J., Loe, B.S., Cheke, L., Mart\u00ednez-Plumed, F., \u00d3\u00a0h\u00e9igeartaigh, S.: General intelligence disentangled via a generality metric for natural and artificial intelligence. Sci. Rep. 11(1), 22822 (2021)","DOI":"10.1038\/s41598-021-01997-7"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"H\u00e9rnandez-Orallo, J., et\u00a0al.: A new ai evaluation cosmos: Ready to play the game? AI Maga. 38 (2017). https:\/\/www.microsoft.com\/en-us\/research\/publication\/new-ai-evaluation-cosmos-ready-play-game\/","DOI":"10.1609\/aimag.v38i3.2748"},{"key":"18_CR10","unstructured":"Legg, S.: Machine super intelligence. Ph.D. thesis, Universit\u00e0 della Svizzera italiana (2008)"},{"key":"18_CR11","unstructured":"Meier, R., Mujika, A.: Open-ended reinforcement learning with neural reward functions (2022). https:\/\/arxiv.org\/abs\/2202.08266"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Mesnage, C.: Thinking as an action. In: The 17th Annual AGI Conference, Seattle, WA, USA, 13\u201316 August 2024. Springer (2024)","DOI":"10.1007\/978-3-031-65572-2_14"},{"key":"18_CR13","unstructured":"Mnih, V., et\u00a0al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"18_CR14","unstructured":"Morris, M.R., et\u00a0al.: Levels of AGI for operationalizing progress on the path to AGI (2024). https:\/\/arxiv.org\/abs\/2311.02462"},{"key":"18_CR15","doi-asserted-by":"publisher","unstructured":"Bakhtin, A., et\u00a0al.: Human-level play in the game of $$<$$i$$>$$diplomacy$$<$$\/i$$>$$ by combining language models with strategic reasoning. Science 378(6624), 1067\u20131074 (2022). https:\/\/doi.org\/10.1126\/science.ade9097. https:\/\/www.science.org\/doi\/abs\/10.1126\/science.ade9097","DOI":"10.1126\/science.ade9097"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Orzan, N., Acar, E., Grossi, D., R\u0103dulescu, R.: Learning in public goods games with non-linear utilities: a multi-objective approach. In: The Sixteenth Workshop on Adaptive and Learning Agents (2024). https:\/\/openreview.net\/forum?id=1GXIiEo9wj","DOI":"10.3233\/FAIA240809"},{"key":"18_CR17","unstructured":"Park, S., Rybkin, O., Levine, S.: Metra: scalable unsupervised rl with metric-aware abstraction (2024). https:\/\/arxiv.org\/abs\/2310.08887"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: International Conference on Machine Learning, pp. 2778\u20132787. PMLR (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"18_CR19","unstructured":"Perez-Liebana, D., et\u00a0al.: The multi-agent reinforcement learning in malm\u00f6 (marl\u00f6) competition. arXiv preprint arXiv:1901.08129 (2019)"},{"key":"18_CR20","doi-asserted-by":"publisher","unstructured":"Potapov, A., Belikov, A., Scherbakov, O., Bogdanov, V.: General-purpose minecraft agents and hybrid AGI. In: Artificial General Intelligence: 15th International Conference, AGI 2022, Seattle, WA, USA, 19\u201322 August 2022, Proceedings, pp. 75\u201385. Springer, Heidelberg (2023). https:\/\/doi.org\/10.1007\/978-3-031-19907-3_8","DOI":"10.1007\/978-3-031-19907-3_8"},{"key":"18_CR21","unstructured":"R\u00f6pke, W., Reymond, M., Mannion, P., Roijers, D.M., Now\u00e9, A., R\u0103dulescu, R.: Divide and conquer: provably unveiling the pareto front with multi-objective reinforcement learning (2024). https:\/\/arxiv.org\/abs\/2402.07182"},{"issue":"7839","key":"18_CR22","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser, J., et al.: Mastering atari, go, chess and shogi by planning with a learned model. Nature 588(7839), 604\u2013609 (2020)","journal-title":"Nature"},{"key":"18_CR23","unstructured":"Srivastava, R.K., Shyam, P., Mutz, F., Ja\u015bkowski, W., Schmidhuber, J.: Training agents using upside-down reinforcement learning. arXiv preprint arXiv:1912.02877 (2019)"},{"key":"18_CR24","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (2018)"},{"issue":"1\u20132","key":"18_CR25","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/s0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between mdps and semi-mdps: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1\u20132), 181\u2013211 (1999). https:\/\/doi.org\/10.1016\/s0004-3702(99)00052-1","journal-title":"Artif. Intell."},{"key":"18_CR26","unstructured":"Taylor, R., et\u00a0al.: Galactica: a large language model for science (2022)"},{"key":"18_CR27","unstructured":"Team, S., et\u00a0al.: Scaling instructable agents across many simulated worlds (2024). https:\/\/arxiv.org\/abs\/2404.10179"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Torrado, R.R., Bontrager, P., Togelius, J., Liu, J., Perez-Liebana, D.: Deep reinforcement learning for general video game AI. In: 2018 IEEE Conference on Computational Intelligence and Games (CIG). IEEE (2018)","DOI":"10.1109\/CIG.2018.8490422"},{"key":"18_CR29","unstructured":"Vamplew, P., et\u00a0al.: Utility-based reinforcement learning: Unifying single-objective and multi-objective reinforcement learning (2024). https:\/\/arxiv.org\/abs\/2402.02665"},{"key":"18_CR30","unstructured":"Wang, G., et\u00a0al.: Voyager: an open-ended embodied agent with large language models. In: Intrinsically-Motivated and Open-Ended Learning Workshop@ NeurIPS2023 (2023)"},{"key":"18_CR31","doi-asserted-by":"publisher","unstructured":"Xu, B., Ren, Q.: Artificial open world for evaluating AGI: a conceptual design. In: Artificial General Intelligence: 15th International Conference, AGI 2022, Seattle, WA, USA, 19\u201322 August 2022, Proceedings, pp. 452\u2013463. Springer, Heidelberg (2023). https:\/\/doi.org\/10.1007\/978-3-031-19907-3_43","DOI":"10.1007\/978-3-031-19907-3_43"}],"container-title":["Lecture Notes in Computer Science","Artificial General Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-00800-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T21:04:37Z","timestamp":1757365477000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-00800-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,7]]},"ISBN":["9783032007995","9783032008008"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-00800-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,7]]},"assertion":[{"value":"7 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial General Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Reykjavic","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Iceland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"agi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/agi-conf.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}