{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T03:44:02Z","timestamp":1771991042206,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T00:00:00Z","timestamp":1632873600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T00:00:00Z","timestamp":1632873600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"National Science Foundation","award":["IIS-1526813"],"award-info":[{"award-number":["IIS-1526813"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Swarm Intell"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s11721-021-00203-8","type":"journal-article","created":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T12:03:16Z","timestamp":1632916996000},"page":"29-58","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Reinforcement learning as a rehearsal for swarm foraging"],"prefix":"10.1007","volume":"16","author":[{"given":"Trung","family":"Nguyen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7999-0307","authenticated-orcid":false,"given":"Bikramjit","family":"Banerjee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,29]]},"reference":[{"key":"203_CR1","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.neucom.2015.05.116","volume":"172","author":"L Bayindir","year":"2016","unstructured":"Bayindir, L. (2016). A review of swarm robotics tasks. Neurocomputing, 172, 292\u2013321. https:\/\/doi.org\/10.1016\/j.neucom.2015.05.116.","journal-title":"Neurocomputing"},{"issue":"3","key":"203_CR2","doi-asserted-by":"publisher","first-page":"038101","DOI":"10.1103\/PhysRevLett.112.038101","volume":"112","author":"T Biancalani","year":"2014","unstructured":"Biancalani, T., Dyson, L., & McKane, A. J. (2014). Noise-induced bistable states and their mean switching time in foraging colonies. Physical Review Letters, 112(3), 038101.","journal-title":"Physical Review Letters"},{"key":"203_CR3","volume-title":"Pattern recognition and machine learning (information science and statistics)","author":"CM Bishop","year":"2007","unstructured":"Bishop, C. M. (2007). Pattern recognition and machine learning (information science and statistics). Springer."},{"issue":"1","key":"203_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11721-012-0075-2","volume":"7","author":"M Brambilla","year":"2013","unstructured":"Brambilla, M., Ferrante, E., Birattari, M., & Dorigo, M. (2013). Swarm robotics: A review from the swarm engineering perspective. Swarm Intelligence, 7(1), 1\u201341.","journal-title":"Swarm Intelligence"},{"key":"203_CR5","unstructured":"Claus, C., & Boutilier, C. (1998). The dynamics of reinforcement learning in cooperative multiagent systems. In Proceedings of the 15th national conference on artificial intelligence (pp. 746\u2013752). AAAI Press\/MIT Press."},{"key":"203_CR6","doi-asserted-by":"crossref","unstructured":"Correll, N., & Martinoli, A. (2006). Collective inspection of regular structures using a swarm of miniature robots. In 9th int. symp. on experimental robotics (ISER) (pp. 375\u2013385). Springer Tracts in Advanced Robotics.","DOI":"10.1007\/11552246_36"},{"issue":"2","key":"203_CR7","first-page":"188","volume":"216","author":"TJ Czaczkes","year":"2013","unstructured":"Czaczkes, T. J., Gr\u00fcter, C., Ellis, L., Wood, E., & Ratnieks, F. L. (2013). Ant foraging on complex trails: Route learning and the role of trail pheromones in Lasius niger. Journal of Experimental Biology, 216(2), 188\u2013197.","journal-title":"Journal of Experimental Biology"},{"key":"203_CR8","doi-asserted-by":"crossref","unstructured":"Dimidov, C., Oriolo, G., & Trianni, V. (2016). Random walks in swarm robotics: An experiment with kilobots. In International conference on swarm intelligence (pp. 185\u2013196). Springer.","DOI":"10.1007\/978-3-319-44427-7_16"},{"issue":"4","key":"203_CR9","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1109\/MRA.2013.2252996","volume":"20","author":"M Dorigo","year":"2013","unstructured":"Dorigo, M., Floreano, D., Gambardella, L. M., Mondada, F., Nolfi, S., Baaboura, T., et al. (2013). Swarmanoid: A novel concept for the study of heterogeneous robotic swarms. IEEE Robotics & Automation Magazine, 20(4), 60\u201371.","journal-title":"IEEE Robotics & Automation Magazine"},{"issue":"7","key":"203_CR10","doi-asserted-by":"publisher","first-page":"1152","DOI":"10.1109\/JPROC.2021.3072740","volume":"109","author":"M Dorigo","year":"2021","unstructured":"Dorigo, M., Theraulaz, G., & Trianni, V. (2021). Swarm robotics: Past, present, and future. Proceedings of the IEEE, 109(7), 1152\u20131165. https:\/\/doi.org\/10.1109\/JPROC.2021.3072740.","journal-title":"Proceedings of the IEEE"},{"key":"203_CR11","first-page":"607","volume":"7","author":"SV Essche","year":"2015","unstructured":"Essche, S. V., Ferrante, E., Turgut, A. E., Lon, R. V., Holvoet, T., & Wenseleers, T. (2015). Environmental factors promoting the evolution of recruitment strategies in swarms of foraging robots. Proceedings of the First International Symposium on Swarm Behavior and Bio-Inspired Robotics, 7, 607\u2013613.","journal-title":"Proceedings of the First International Symposium on Swarm Behavior and Bio-Inspired Robotics"},{"issue":"8","key":"203_CR12","doi-asserted-by":"publisher","first-page":"e1004273","DOI":"10.1371\/journal.pcbi.1004273","volume":"11","author":"E Ferrante","year":"2015","unstructured":"Ferrante, E., Turgut, A. E., Du\u00e9\u00f1ez-Guzm\u00e1n, E., Dorigo, M., & Wenseleers, T. (2015). Evolution of self-organized task specialization in robot swarms. PLoS Computational Biology, 11(8), e1004273.","journal-title":"PLoS Computational Biology"},{"issue":"3","key":"203_CR13","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/s11721-014-0097-z","volume":"8","author":"R Fujisawa","year":"2014","unstructured":"Fujisawa, R., Dobata, S., Sugawara, K., & Matsuno, F. (2014). Designing pheromone communication in swarm robotics: Group foraging behavior mediated by chemical substance. Swarm Intelligence, 8(3), 227\u2013246.","journal-title":"Swarm Intelligence"},{"key":"203_CR14","volume-title":"Handbook of stochastic methods","author":"CW Gardiner","year":"1985","unstructured":"Gardiner, C. W. (1985). Handbook of stochastic methods (Vol. 3). Springer."},{"key":"203_CR15","unstructured":"Goldberg, D., & Mataric, M. J. (1997). Interference as a tool for designing and evaluating multi-robot controllers. In AAAI\/IAAI (pp. 637\u2013642)."},{"key":"203_CR16","unstructured":"Goldberg, D., & Mataric, M. J. (2000). Robust behavior-based control for distributed multi-robot collection tasks. In Technical report IRIS-00-387. USC Institute for Robotics and Intelligent Systems."},{"key":"203_CR17","unstructured":"Goss, S., & Deneubourg, J. L. (1992). Harvesting by a group of robots. In First European conference on artificial life (pp. 195\u2013204)."},{"key":"203_CR18","doi-asserted-by":"crossref","unstructured":"Hamann, H. (2018). Superlinear scalability in parallel computing and multi-robot systems: Shared resources, collaboration, and network topology. In International conference on architecture of computing systems (pp. 31\u201342). Springer.","DOI":"10.1007\/978-3-319-77610-1_3"},{"key":"203_CR19","doi-asserted-by":"publisher","unstructured":"Hecker, J. P., & Moses, M. E. (2013). An evolutionary approach for robust adaptation of robot behavior to sensor error. In Proceeding of the fifteenth annual conference companion on genetic and evolutionary computation conference companion\u2014GECCO \u201913 companion. https:\/\/doi.org\/10.1145\/2464576.2482724","DOI":"10.1145\/2464576.2482724"},{"issue":"1","key":"203_CR20","first-page":"43","volume":"9","author":"JP Hecker","year":"2015","unstructured":"Hecker, J. P., & Moses, M. E. (2015). Beyond pheromones: Evolving error-tolerant, flexible, and scalable ant-inspired robot swarms. Swarm Intelligence, 9(1), 43\u201370.","journal-title":"Swarm Intelligence"},{"key":"203_CR21","doi-asserted-by":"crossref","unstructured":"Hoff, N., Sagoff, A., Wood, R., & Nagpal, R. (2010). Two foraging algorithms for robot swarms using only local communication. In Proc. IEEE international conference on robotics and biomimetics.","DOI":"10.1109\/ROBIO.2010.5723314"},{"key":"203_CR22","doi-asserted-by":"crossref","unstructured":"Kengyel, D., Hamann, H., Zahadat, P., Radspieler, G., Wotawa, F., & Schmickl, T. (2015). Potential of heterogeneity in collective behaviors: A case study on heterogeneous swarms. In International conference on principles and practice of multi-agent systems (pp. 201\u2013217). Springer.","DOI":"10.1007\/978-3-319-25524-8_13"},{"issue":"2","key":"203_CR23","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s11721-017-0137-6","volume":"11","author":"Y Khaluf","year":"2017","unstructured":"Khaluf, Y., Pinciroli, C., Valentini, G., & Hamann, H. (2017). The impact of agent density on scalability in collective systems: Noise-induced versus majority-based bistability. Swarm Intelligence, 11(2), 155\u2013179.","journal-title":"Swarm Intelligence"},{"key":"203_CR24","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.neucom.2016.01.031","volume":"190","author":"L Kraemer","year":"2016","unstructured":"Kraemer, L., & Banerjee, B. (2016). Multi-agent reinforcement learning as a rehearsal for decentralized planning. Neurocomputing, 190, 82\u201394.","journal-title":"Neurocomputing"},{"key":"203_CR25","doi-asserted-by":"crossref","unstructured":"Kumar, V., & Sahin, F. (2003). Cognitive maps in swarm robots for the mine detection application. In Proc. IEEE international conference on systems, man and cybernetics (Vol.\u00a04, pp. 3364\u20133369).","DOI":"10.1109\/ICSMC.2003.1244409"},{"issue":"1","key":"203_CR26","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1145\/1152934.1152936","volume":"1","author":"TH Labella","year":"2006","unstructured":"Labella, T. H., Dorigo, M., & Deneubourg, J. L. (2006). Division of labor in a group of robots inspired by ants\u2019 foraging behavior. ACM Transactions on Autonomous and Adaptive Systems (TAAS), 1(1), 4\u201325.","journal-title":"ACM Transactions on Autonomous and Adaptive Systems (TAAS)"},{"key":"203_CR27","doi-asserted-by":"publisher","unstructured":"Letendre, K., & Moses, M. E. (2013). Synergy in ant foraging strategies. In Proceeding of the fifteenth annual conference on genetic and evolutionary computation conference\u2014GECCO \u201913. https:\/\/doi.org\/10.1145\/2463372.2463389","DOI":"10.1145\/2463372.2463389"},{"key":"203_CR28","unstructured":"Liemhetcharat, S., Yan, R., & Tee, K. P. (2015). Continuous foraging and information gathering in a multi-agent team. In Proceedings of the 2015 international conference on autonomous agents and multiagent systems (pp. 1325\u20131333)."},{"key":"203_CR29","doi-asserted-by":"crossref","unstructured":"Llenas, A. F., Talamali, M. S., Xu, X., Marshall, J. A., & Reina, A. (2018). Quality-sensitive foraging by a robot swarm through virtual pheromone trails. In International conference on swarm intelligence (pp. 135\u2013149). Springer.","DOI":"10.1007\/978-3-030-00533-7_11"},{"key":"203_CR30","doi-asserted-by":"crossref","unstructured":"Lu, Q., Moses, M. E., & Hecker, J. P. (2016). A scalable and adaptable multiple-place foraging algorithm for ant-inspired robot swarms. In Robotics: Science and systems conference (RSS 2016) workshop.","DOI":"10.1109\/IROS.2016.7759561"},{"key":"203_CR31","doi-asserted-by":"crossref","unstructured":"Mayya, S., Pierpaoli, P., & Egerstedt, M. (2019). Voluntary retreat for decentralized interference reduction in robot swarms. In 2019 international conference on robotics and automation (ICRA) (pp. 9667\u20139673). IEEE.","DOI":"10.1109\/ICRA.2019.8794124"},{"key":"203_CR32","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., et al. (2015). Human-level control through deep reinforcement learning. Nature, 518, 529\u2013533.","journal-title":"Nature"},{"key":"203_CR33","doi-asserted-by":"crossref","unstructured":"P\u00e9rez, I. F., Boumaza, A., & Charpillet, F. (2017). Learning collaborative foraging in a swarm of robots using embodied evolution. In Artificial life conference proceedings 14 (pp. 162\u2013161). MIT Press.","DOI":"10.7551\/ecal_a_028"},{"issue":"4","key":"203_CR34","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/s11721-012-0072-5","volume":"6","author":"C Pinciroli","year":"2012","unstructured":"Pinciroli, C., Trianni, V., O\u2019Grady, R., Pini, G., Brutschy, A., Brambilla, M., et al. (2012). Argos: A modular, parallel, multi-engine simulator for multi-robot systems. Swarm Intelligence, 6(4), 271\u2013295.","journal-title":"Swarm Intelligence"},{"issue":"1","key":"203_CR35","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11721-016-0118-1","volume":"10","author":"L Pitonakova","year":"2016","unstructured":"Pitonakova, L., Crowder, R., & Bullock, S. (2016). Information flow principles for plasticity in foraging robot swarms. Swarm Intelligence, 10(1), 33\u201363.","journal-title":"Swarm Intelligence"},{"issue":"1","key":"203_CR36","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s11721-017-0148-3","volume":"12","author":"L Pitonakova","year":"2018","unstructured":"Pitonakova, L., Crowder, R., & Bullock, S. (2018). The information-cost-reward framework for understanding robot swarm foraging. Swarm Intelligence, 12(1), 71\u201396.","journal-title":"Swarm Intelligence"},{"key":"203_CR37","doi-asserted-by":"publisher","first-page":"e48945","DOI":"10.7554\/eLife.48945","volume":"8","author":"LA Poissonnier","year":"2019","unstructured":"Poissonnier, L. A., Motsch, S., Gautrais, J., Buhl, J., & Dussutour, A. (2019). Experimental investigation of ant traffic under crowded conditions. Elife, 8, e48945.","journal-title":"Elife"},{"issue":"2","key":"203_CR38","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/s11721-015-0105-y","volume":"9","author":"A Reina","year":"2015","unstructured":"Reina, A., Miletitch, R., Dorigo, M., & Trianni, V. (2015). A quantitative micro-macro link for collective decisions: The shortest path discovery\/selection example. Swarm Intelligence, 9(2), 75\u2013102.","journal-title":"Swarm Intelligence"},{"key":"203_CR39","doi-asserted-by":"crossref","unstructured":"Riedmiller, M. (2005). Neural fitted Q iteration: First experiences with a data efficient neural reinforcement learning method. In Proceedings of European conference on machine learning (pp. 317\u2013328). Springer.","DOI":"10.1007\/11564096_32"},{"key":"203_CR40","doi-asserted-by":"crossref","unstructured":"Saha, H. N., Das, N. K., Pal, S. K., Basu, S., Auddy, S., Dey, R., Nandy, A., Pal, D., Roy, N., Mitra, D., & Biswas, S. (2018). A cloud based autonomous multipurpose system with self-communicating bots and swarm of drones. In 2018 IEEE 8th annual computing and communication workshop and conference (CCWC) (pp. 649\u2013653). IEEE.","DOI":"10.1109\/CCWC.2018.8301781"},{"key":"203_CR41","doi-asserted-by":"crossref","unstructured":"\u015eahin, E., Girgin, S., Bayindir, L., & Turgut, A. E. (2008). Swarm robotics. In Swarm intelligence (pp. 87\u2013100). Springer.","DOI":"10.1007\/978-3-540-74089-6_3"},{"key":"203_CR42","unstructured":"Schaul, T., Quan, J., Antonoglou, I., & Silver, D. (2015). Prioritized experience replay. arXiv preprint arXiv:1511.05952"},{"issue":"2","key":"203_CR43","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s11721-014-0093-3","volume":"8","author":"O Simonin","year":"2014","unstructured":"Simonin, O., Charpillet, F., & Thierry, E. (2014). Revisiting wavefront construction with collective agents: An approach to foraging. Swarm Intelligence, 8(2), 113\u2013138. https:\/\/doi.org\/10.1007\/s11721-014-0093-3.","journal-title":"Swarm Intelligence"},{"key":"203_CR44","volume-title":"Reinforcement learning: An introduction","author":"R Sutton","year":"1998","unstructured":"Sutton, R., & Barto, A. G. (1998). Reinforcement learning: An introduction. MIT Press."},{"issue":"1","key":"203_CR45","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/s11721-019-00176-9","volume":"14","author":"MS Talamali","year":"2020","unstructured":"Talamali, M. S., Bose, T., Haire, M., Xu, X., Marshall, J. A., & Reina, A. (2020). Sophisticated collective foraging with minimalist agents: A swarm robotics test. Swarm Intelligence, 14(1), 25\u201356.","journal-title":"Swarm Intelligence"},{"key":"203_CR46","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt, H., Guez, A., & Silver, D. (2016). Deep reinforcement learning with double q-learning. In Proceedings of the thirtieth AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"203_CR47","unstructured":"Wang, Z., Schaul, T,, Hessel, M., Van\u00a0Hasselt, H., Lanctot, M., & De\u00a0Freitas, N. (2015). Dueling network architectures for deep reinforcement learning. arXiv preprint arXiv:1511.06581"},{"key":"203_CR48","first-page":"279","volume":"8","author":"C Watkins","year":"1992","unstructured":"Watkins, C., & Dayan, P. (1992). Q-learning: Technical note. Machine Learning, 8, 279\u2013292.","journal-title":"Machine Learning"},{"issue":"3","key":"203_CR49","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/s12597-012-0077-2","volume":"49","author":"M Yogeswaran","year":"2012","unstructured":"Yogeswaran, M., & Ponnambalam, S. G. (2012). Reinforcement learning: Exploration-exploitation dilemma in multi-agent foraging task. Opsearch, 49(3), 223\u2013236. https:\/\/doi.org\/10.1007\/s12597-012-0077-2.","journal-title":"Opsearch"}],"container-title":["Swarm Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11721-021-00203-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11721-021-00203-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11721-021-00203-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T18:59:51Z","timestamp":1673377191000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11721-021-00203-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,29]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["203"],"URL":"https:\/\/doi.org\/10.1007\/s11721-021-00203-8","relation":{},"ISSN":["1935-3812","1935-3820"],"issn-type":[{"value":"1935-3812","type":"print"},{"value":"1935-3820","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,29]]},"assertion":[{"value":"5 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 September 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}