{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:35:40Z","timestamp":1742913340503,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031746499"},{"type":"electronic","value":"9783031746505"}],"license":[{"start":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:00:00Z","timestamp":1730505600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:00:00Z","timestamp":1730505600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-74650-5_8","type":"book-chapter","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T15:51:27Z","timestamp":1732809087000},"page":"135-154","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Laser Learning Environment: A New Environment for\u00a0Coordination-Critical Multi-agent Tasks"],"prefix":"10.1007","author":[{"given":"Yannick","family":"Molinghen","sequence":"first","affiliation":[]},{"given":"Rapha\u00ebl","family":"Avalos","sequence":"additional","affiliation":[]},{"given":"Mark","family":"Van Achter","sequence":"additional","affiliation":[]},{"given":"Ann","family":"Now\u00e9","sequence":"additional","affiliation":[]},{"given":"Tom","family":"Lenaerts","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,2]]},"reference":[{"key":"8_CR1","unstructured":"Amodei, D., Olah, C., Steinhardt, J., Christiano, P.F., Schulman, J., Man\u00e9, D.: Concrete problems in AI safety. CoRR, abs\/1606.06565 (2016)"},{"key":"8_CR2","unstructured":"Avalos, R., Reymond, M., Now\u00e9, A., Roijers, D.M.: Local advantage networks for cooperative multi-agent reinforcement learning. In: AAMAS 2022: Proceedings of the 21st International Conference on Autonomous Agents and MultiAgent Systems (Extended Abstract) (2022)"},{"key":"8_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2019.103216","volume":"280","author":"N Bard","year":"2020","unstructured":"Bard, N., et al.: The hanabi challenge: a new frontier for AI research. Artif. Intell. 280, 103216 (2020). ISSN: 00043702","journal-title":"Artif. Intell."},{"key":"8_CR4","unstructured":"Boutilier, C.: Planning, learning and coordination in multiagent decision processes. In: Proceedings of the 6th Conference on Theoretical Aspects of Rationality and Knowledge, pp. 195\u2013210 (1996)"},{"key":"8_CR5","unstructured":"Burda, Y., Edwards, H., Storkey, A., Klimov, O.: Exploration by random network distillation (2018)"},{"issue":"1","key":"8_CR6","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1109\/TII.2012.2219061","volume":"9","author":"Y Cao","year":"2013","unstructured":"Cao, Y., Wenwu, Yu., Ren, W., Chen, G.: An overview of recent progress in the study of distributed multi-agent coordination. IEEE Trans. Ind. Inf. 9(1), 427\u2013438 (2013)","journal-title":"IEEE Trans. Ind. Inf."},{"key":"8_CR7","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence and Tenth Innovative Applications of Artificial Intelligence Conference, AAAI 1998 (1998)"},{"key":"8_CR8","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3389\/frobt.2018.00054","volume":"5","author":"R Klima","year":"2018","unstructured":"Klima, R., et al.: Space debris removal: learning to cooperate and the price of anarchy. Front. Robot. AI 5, 54 (2018). ISSN: 2296-9144","journal-title":"Front. Robot. AI"},{"issue":"1","key":"8_CR9","first-page":"55","volume":"15","author":"GJ Laurent","year":"2011","unstructured":"Laurent, G.J., Matignon, L., Le Fort-Piat, N.: The world of independent learners is not Markovian. Int. J. Knowl.-Based Intell. Eng. Syst. 15(1), 55\u201364 (2011). ISSN: 18758827, 13272314","journal-title":"Int. J. Knowl.-Based Intell. Eng. Syst."},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Ha, P.: Gradient-based learning applied to document recognition (1998)","DOI":"10.1109\/5.726791"},{"key":"8_CR11","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: Bengio, Y., LeCun, Y. (eds.) ICLR (2016)"},{"key":"8_CR12","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Neural Information Processing Systems (NIPS) (2017)"},{"issue":"7540","key":"8_CR13","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015). ISSN: 1476-4687","journal-title":"Nature"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Mordatch, I., Abbeel, P.: Emergence of grounded compositional language in multi-agent populations. arXiv preprint arXiv:1703.04908 (2017)","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"8_CR15","series-title":"SpringerBriefs in Intelligent Systems","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8","volume-title":"A Concise Introduction to Decentralized POMDPs","author":"FA Oliehoek","year":"2016","unstructured":"Oliehoek, F.A., Amato, C.: A Concise Introduction to Decentralized POMDPs. SpringerBriefs in Intelligent Systems, Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-28929-8. ISBN: 978-3-319-28929-8"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Oliehoek, F.A., Spaan, M.T.J., Vlassis, N.: Optimal and approximate Q-value functions for decentralized POMDPs. J. Artif. Intell. Res. 32, 289\u2013353 (2008a). ISSN: 1076-9757","DOI":"10.1613\/jair.2447"},{"key":"8_CR17","unstructured":"Oliehoek, F.A., Spaan, M.T.J., Whiteson, S.: Exploiting locality of interaction in factored Dec-POMDPs. In: International Joint Conference on Autonomous Agents and Multi-Agent Systems, pp. 517\u2013524 (2008b)"},{"issue":"3","key":"8_CR18","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s10458-005-2631-2","volume":"11","author":"L Panait","year":"2005","unstructured":"Panait, L., Luke, S.: Cooperative multi-agent learning: the state of the art. Auton. Agents Multi-Agent Syst. 11(3), 387\u2013434 (2005). ISSN: 1573-7454","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"8_CR19","unstructured":"Parker-Holder, J., et al.: Evolving curricula with regret-based environment design. In: International Conference on Machine Learning, pp. 17473\u201317498. PMLR (2022)"},{"key":"8_CR20","unstructured":"Rashid, T., Samvelyan, M., De Witt, C.S.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning (2018)"},{"key":"8_CR21","unstructured":"Samvelyan, M., et al.: The StarCraft multi-agent challenge. CoRR, abs\/1902.04043 (2019)"},{"key":"8_CR22","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. In: 4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings, pp. 1\u201321 (2016)"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: A possibility for implementing curiosity and boredom in model-building neural controllers. In: Meyer, J.-A. (ed.) From Animals to Animats, pp. 222\u2013227. The MIT Press (1991). International Conference on Simulation Adaptive Behavior: From Animals to Animats Edition. ISBN: 978-0-262-25667-4","DOI":"10.7551\/mitpress\/3115.003.0030"},{"key":"8_CR24","unstructured":"Son, K., Kim, D., Kang, W.J., Hostallero, D.E., Yi, Y.: QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning (2019)"},{"key":"8_CR25","unstructured":"Stern, R., et al.: Multi-agent pathfinding: definitions, variants, and benchmarks (2017)"},{"key":"8_CR26","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning based on team reward. In: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, vol. 3, pp. 2085\u20132087 (2018). ISSN: 15582914. ISBN: 9781510868083"},{"key":"8_CR27","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction (2018)"},{"key":"8_CR28","unstructured":"Sutton, R.S.: Temporal credit assignment in reinforcement learning. Ph.D. thesis, University of Massachusetts Amherst (1984). AAI8410337"},{"issue":"3","key":"8_CR29","first-page":"41","volume":"33","author":"K Tuyls","year":"2012","unstructured":"Tuyls, K., Weiss, G.: Multiagent learning: basics, challenges, and prospects. AI Mag. 33(3), 41 (2012). ISSN: 2371-9621, 0738-4602","journal-title":"AI Mag."},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning (2016). ISBN: 9781577357605","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"8_CR31","unstructured":"van Hasselt, H., Doron, Y., Strub, F., Hessel, M., Sonnerat, N., Modayil, J.: Deep reinforcement learning and the deadly triad (2018)"},{"key":"8_CR32","unstructured":"Watkins, C.: Learning from delayed rewards. Ph.D. thesis, University of Cambridge (1989)"},{"key":"8_CR33","unstructured":"Wu, S.A., Wang, R.E., Evans, J.A., Tenenbaum, J.B., Parkes, D.C., Kleiman-Weiner, M.: Too many cooks: coordinating multi-agent collaboration through inverse planning. Topics in Cognitive Science (2021)"}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence and Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-74650-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T16:03:48Z","timestamp":1732809828000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-74650-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,2]]},"ISBN":["9783031746499","9783031746505"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-74650-5_8","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024,11,2]]},"assertion":[{"value":"2 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BNAIC\/Benelearn","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Benelux Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Delft","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bnaic2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/bnaic2023.tudelft.nl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}