{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T02:44:18Z","timestamp":1775529858175,"version":"3.50.1"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031514968","type":"print"},{"value":"9783031514975","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-51497-5_4","type":"book-chapter","created":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T09:16:09Z","timestamp":1706692569000},"page":"42-56","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["VMAS: A Vectorized Multi-agent Simulator for\u00a0Collective Robot Learning"],"prefix":"10.1007","author":[{"given":"Matteo","family":"Bettini","sequence":"first","affiliation":[]},{"given":"Ryan","family":"Kortvelesy","sequence":"additional","affiliation":[]},{"given":"Jan","family":"Blumenkamp","sequence":"additional","affiliation":[]},{"given":"Amanda","family":"Prorok","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,2,1]]},"reference":[{"key":"4_CR1","unstructured":"Pyglet. https:\/\/pyglet.org\/"},{"key":"4_CR2","unstructured":"Baker, B., et al.: Emergent tool use from multi-agent autocurricula. In: International Conference on Learning Representations (2019)"},{"issue":"4","key":"4_CR3","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1287\/moor.27.4.819.297","volume":"27","author":"DS Bernstein","year":"2002","unstructured":"Bernstein, D.S., Givan, R., Immerman, N., Zilberstein, S.: The complexity of decentralized control of markov decision processes. Math. Oper. Res. 27(4), 819\u2013840 (2002)","journal-title":"Math. Oper. Res."},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Blumenkamp, J., Morad, S., Gielis, J., Li, Q., Prorok, A.: A framework for real-world multi-robot systems running decentralized gnn-based policies. arXiv preprint arXiv:2111.01777 (2021)","DOI":"10.1109\/ICRA46639.2022.9811744"},{"key":"4_CR5","unstructured":"Bradbury, J., et al.: JAX: composable transformations of Python+NumPy programs (2018). http:\/\/github.com\/google\/jax"},{"issue":"1","key":"4_CR6","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1287\/trsc.1030.0057","volume":"39","author":"O Br\u00e4ysy","year":"2005","unstructured":"Br\u00e4ysy, O., Gendreau, M.: Vehicle routing problem with time windows, Part II: Metaheuristics. Transp. Sci. 39(1), 119\u2013139 (2005)","journal-title":"Transp. Sci."},{"key":"4_CR7","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"4_CR8","unstructured":"Freeman, C.D., Frey, E., Raichuk, A., Girgin, S., Mordatch, I., Bachem, O.: Brax - a differentiable physics engine for large scale rigid body simulation (2021). http:\/\/github.com\/google\/brax"},{"issue":"2","key":"4_CR9","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1023\/A:1011227210047","volume":"11","author":"AJ Ijspeert","year":"2001","unstructured":"Ijspeert, A.J., Martinoli, A., Billard, A., Gambardella, L.M.: Collaboration through the exploitation of local interactions in autonomous collective robotics: the stick pulling experiment. Auton. Robot. 11(2), 149\u2013171 (2001)","journal-title":"Auton. Robot."},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, S., Amato, C.: Multi-agent reinforcement learning with directed exploration and selective memory reuse. In: Proceedings of the 36th Annual ACM Symposium on Applied Computing, pp. 777\u2013784 (2021)","DOI":"10.1145\/3412841.3441953"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Koenig, N., Howard, A.: Design and use paradigms for gazebo, an open-source multi-robot simulator. In: 2004 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No. 04CH37566), pp. 2149\u20132154. IEEE (2004)","DOI":"10.1109\/IROS.2004.1389727"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Kurach, K., et al.: Google research football: a novel reinforcement learning environment. Proc. AAAI Conf. Artif. Intell. 34, 4501\u20134510 (2020)","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"4_CR13","unstructured":"Lange, R.T.: gymnax: A JAX-based reinforcement learning environment library (2022). http:\/\/github.com\/RobertTLange\/gymnax"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Li, Q., Gama, F., Ribeiro, A., Prorok, A.: Graph neural networks for decentralized multi-robot path planning. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 11785\u201311792. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341668"},{"key":"4_CR15","unstructured":"Liang, E., et al.: Rllib: abstractions for distributed reinforcement learning. In: International Conference on Machine Learning, pp. 3053\u20133062. PMLR (2018)"},{"key":"4_CR16","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. Adv. Neural Inf. Process. Syst. (2017)"},{"key":"4_CR17","unstructured":"Makoviychuk, V., et al.: Isaac gym: High performance GPU based physics simulation for robot learning. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Michel, O.: Cyberbotics ltd. webots$$^{\\rm TM}$$: professional mobile robot simulation. Int. J. Adv. Robot. Syst. 1, 5 (2004)","DOI":"10.5772\/5618"},{"key":"4_CR19","unstructured":"Niiranen, J.: Fast and accurate symmetric Euler algorithm for electromechanical simulations. In: Electrimacs 99 (Modelling and Simulation of Electric Machines Converters an & Systems), pp. I\u201371 (D1999)"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Noori, F.M., Portugal, D., Rocha, R.P., Couceiro, M.S.: On 3d simulators for multi-robot systems in ros: Morse or gazebo? In: 2017 IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR), pp. 19\u201324 (2017)","DOI":"10.1109\/SSRR.2017.8088134"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Panerati, J., Zheng, H., Zhou, S., Xu, J., Prorok, A., Schoellig, A.P.: Learning to fly-a gym environment with pybullet physics for reinforcement learning of multi-agent quadcopter control. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7512\u20137519. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9635857"},{"key":"4_CR22","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. (2019)"},{"key":"4_CR23","unstructured":"Peng, B., et al.: Facmac: factored multi-agent centralised policy gradients. Adv. Neural Inf. Process. Syst. 12208\u201312221 (2021)"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Pinciroli, C., et al.: ARGoS: a modular, parallel, multi-engine simulator for multi-robot systems. Swarm Intell. 6, 271\u2013295 (2012)","DOI":"10.1007\/s11721-012-0072-5"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Prorok, A.: Robust assignment using redundant robots on transport networks with uncertain travel time. IEEE Trans. Automat. Sci. Eng. 17, 2025\u20132037 (2020)","DOI":"10.1109\/TASE.2020.2986641"},{"key":"4_CR26","unstructured":"Resnick, C., et al.: Pommerman: a multi-agent playground. CoRR (2018)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Reynolds, C.W.: Flocks, herds and schools: a distributed behavioral model. In: Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques, pp. 25\u201334 (1987)","DOI":"10.1145\/37401.37406"},{"key":"4_CR28","unstructured":"Samvelyan, M., et al.: The StarCraft Multi-agent Challenge. CoRR (2019)"},{"key":"4_CR29","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Shen, J., Xiao, E., Liu, Y., Feng, C.: A deep reinforcement learning environment for particle robot navigation and object manipulation. arXiv preprint arXiv:2203.06464 (2022)","DOI":"10.1109\/ICRA46639.2022.9811965"},{"key":"4_CR31","unstructured":"Suarez, J., Du, Y., Isola, P., Mordatch, I.: Neural MMO: a massively multiagent game environment for training and evaluating intelligent agents. arXiv preprint arXiv:1903.00784 (2019)"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: Mujoco: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"4_CR33","unstructured":"Tolstaya, E., Gama, F., Paulos, J., Pappas, G., Kumar, V., Ribeiro, A.: Learning decentralized controllers for robot swarms with graph neural networks. In: Kaelbling, L.P., Kragic, D., Sugiura, K. (eds.) Proceedings of the Conference on Robot Learning, Proceedings of Machine Learning Research, vol. 100, pp. 671\u2013682. PMLR (2020). https:\/\/proceedings.mlr.press\/v100\/tolstaya20a.html"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Wang, B., Liu, Z., Li, Q., Prorok, A.: Mobile robot path planning in dynamic environments through globally guided reinforcement learning. IEEE Robot. Automat. Lett. 5, 6932\u20136939 (2020)","DOI":"10.1109\/LRA.2020.3026638"},{"key":"4_CR35","unstructured":"Weng, J., et al.: Envpool: a highly parallel reinforcement learning environment execution engine. arXiv preprint arXiv:2206.10558 (2022)"},{"key":"4_CR36","unstructured":"de Witt, C.S., et al.: Is independent learning all you need in the starcraft multi-agent challenge? arXiv preprint arXiv:2011.09533 (2020)"},{"key":"4_CR37","unstructured":"Yu, C., Velu, A., Vinitsky, E., Wang, Y., Bayen, A., Wu, Y.: The surprising effectiveness of PPO in cooperative, multi-agent games. arXiv preprint arXiv:2103.01955 (2021)"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, L., et al.: Magent: a many-agent reinforcement learning platform for artificial collective intelligence. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11371"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Zheng, X., Koenig, S., Kempe, D., Jain, S.: Multirobot forest coverage for weighted and unweighted terrain. IEEE Trans. Robot. 26, 1018\u20131031 (2010)","DOI":"10.1109\/TRO.2010.2072271"}],"container-title":["Springer Proceedings in Advanced Robotics","Distributed Autonomous Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-51497-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T16:54:20Z","timestamp":1731171260000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-51497-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031514968","9783031514975"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-51497-5_4","relation":{},"ISSN":["2511-1256","2511-1264"],"issn-type":[{"value":"2511-1256","type":"print"},{"value":"2511-1264","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DARS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Distributed Autonomous Robotic Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Montb\u00e9liard","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dars2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dars2022.org\/#\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}