{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:42:14Z","timestamp":1789083734610,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":105,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585570","type":"print"},{"value":"9783030585587","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58558-7_28","type":"book-chapter","created":{"date-parts":[[2020,10,28]],"date-time":"2020-10-28T09:03:08Z","timestamp":1603875788000},"page":"471-490","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["A Cordial Sync: Going Beyond Marginal Policies for Multi-agent Embodied Tasks"],"prefix":"10.1007","author":[{"given":"Unnat","family":"Jain","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Weihs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Kolve","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Farhadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Svetlana","family":"Lazebnik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aniruddha","family":"Kembhavi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Schwing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,29]]},"reference":[{"key":"28_CR1","unstructured":"Abel, D., Agarwal, A., Diaz, F., Krishnamurthy, A., Schapire, R.E.: Exploratory gradient boosting for reinforcement learning in complex domains. arXiv preprint arXiv:1603.04119 (2016)"},{"key":"28_CR2","unstructured":"Anderson, P., et al.: On evaluation of embodied navigation agents. arXiv preprint arXiv:1807.06757 (2018)"},{"key":"28_CR3","unstructured":"Anderson, P., Shrivastava, A., Parikh, D., Batra, D., Lee, S.: Chasing ghosts: instruction following as bayesian state tracking. In: NeurIPS (2019)"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"28_CR5","unstructured":"Armeni, I., Sax, S., Zamir, A.R., Savarese, S.: Joint 2D\u20133D-semantic data for indoor scene understanding. arXiv preprint arXiv:1702.01105 (2017)"},{"key":"28_CR6","doi-asserted-by":"publisher","first-page":"986","DOI":"10.1109\/TRO.2013.2256686","volume":"29","author":"A Aydemir","year":"2013","unstructured":"Aydemir, A., Pronobis, A., G\u00f6belbecker, M., Jensfelt, P.: Active visual object search in unknown environments using uncertain semantics. IEEE Trans. Robot. 29, 986\u20131002 (2013)","journal-title":"IEEE Trans. Robot."},{"key":"28_CR7","unstructured":"Baker, B., et al.: Emergent tool use from multi-agent autocurricula. arXiv preprint arXiv:1909.07528 (2019)"},{"key":"28_CR8","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"28_CR9","unstructured":"Boutilier, C.: Sequential optimality and coordination in multiagent systems. In: IJCAI (1999)"},{"key":"28_CR10","unstructured":"Bratman, J., Shvartsman, M., Lewis, R.L., Singh, S.: A new approach to exploring language emergence as boundedly optimal control in the face of environmental and cognitive constraints. In: Proceedings of International Conference on Cognitive Modeling (2010)"},{"key":"28_CR11","unstructured":"Brodeur, S., et al.: HoME: a household multimodal environment. arXiv preprint arXiv:1711.11017 (2017)"},{"key":"28_CR12","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","volume":"38","author":"L Busoniu","year":"2008","unstructured":"Busoniu, L., Babuska, R., Schutter, B.D.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern. 38, 156\u2013172 (2008)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"28_CR13","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1109\/TRO.2016.2624754","volume":"32","author":"C Cadena","year":"2016","unstructured":"Cadena, C., et al.: Past, present, and future of simultaneous localization and mapping: toward the robust-perception age. IEEE Trans. Robot. 32, 1309\u20131332 (2016)","journal-title":"IEEE Trans. Robot."},{"key":"28_CR14","volume-title":"The Complexity of Robot Motion Planning","author":"J Canny","year":"1988","unstructured":"Canny, J.: The Complexity of Robot Motion Planning. MIT Press, Cambridge (1988)"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: 3DV (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"28_CR16","unstructured":"Chaplot, D.S., Gupta, S., Gupta, A., Salakhutdinov, R.: Learning to explore using active neural mapping. In: ICLR (2020)"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Chen, B., Song, S., Lipson, H., Vondrick, C.: Visual hide and seek. arXiv preprint arXiv:1910.07882 (2019)","DOI":"10.1162\/isal_a_00269"},{"key":"28_CR18","unstructured":"Chen, C., et al.: Audio-visual embodied navigation. arXiv preprint arXiv:1912.11474 (2019). First two authors contributed equally"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Chen, H., Suhr, A., Misra, D., Snavely, N., Artzi, Y.: Touchdown: natural language navigation and spatial reasoning in visual street environments. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01282"},{"key":"28_CR20","series-title":"Springer Proceedings in Advanced Robotics","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-50115-4_1","volume-title":"2016 International Symposium on Experimental Robotics","author":"S Daftry","year":"2017","unstructured":"Daftry, S., Bagnell, J.A., Hebert, M.: Learning transferable policies for monocular reactive MAV control. In: Kuli\u0107, D., Nakamura, Y., Khatib, O., Venture, G. (eds.) ISER 2016. SPAR, vol. 1, pp. 3\u201311. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-50115-4_1"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Das, A., Datta, S., Gkioxari, G., Lee, S., Parikh, D., Batra, D.: Embodied question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00008"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Das, A., Gkioxari, G., Lee, S., Parikh, D., Batra, D.: Neural modular control for embodied question answering. In: ECCV (2018)","DOI":"10.1109\/CVPR.2018.00008"},{"key":"28_CR23","unstructured":"Das, A., et al.: Probing emergent semantics in predictive agents via question answering. In: ICML (2020). First two authors contributed equally"},{"key":"28_CR24","unstructured":"Das, A., et al.: TarMAC: targeted multi-agent communication. In: ICML (2019)"},{"key":"28_CR25","unstructured":"Dellaert, F., Seitz, S., Thorpe, C., Thrun, S.: Structure from motion without correspondence. In: CVPR (2000)"},{"key":"28_CR26","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/2.30720","volume":"22","author":"A Elfes","year":"1989","unstructured":"Elfes, A.: Using occupancy grids for mobile robot perception and navigation. Computer 22, 46\u201357 (1989)","journal-title":"Computer"},{"key":"28_CR27","unstructured":"Foerster, J.N., Assael, Y.M., de Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: NeurIPS (2016)"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Foerster, J.N., Farquhar, G., Afouras, T., NArdelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"28_CR29","unstructured":"Foerster, J.N., Nardelli, N., Farquhar, G., Torr, P.H.S., Kohli, P., Whiteson, S.: Stabilising experience replay for deep multi-agent reinforcement learning. In: ICML (2017)"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Fraundorfer, F., et al.: Vision-based autonomous mapping and exploration using a quadrotor MAV. In: IROS (2012)","DOI":"10.1109\/IROS.2012.6385934"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Gao, R., Chen, C., Al-Halah, Z., Schissler, C., Grauman, K.: VisualEchoes: spatial image representation learning through echolocation. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58545-7_38"},{"key":"28_CR32","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1007\/978-3-540-45173-0_29","volume-title":"Innovative Concepts for Agent-Based Systems","author":"CL Giles","year":"2003","unstructured":"Giles, C.L., Jim, K.-C.: Learning communication for multi-agent systems. In: Truszkowski, W., Hinchey, M., Rouff, C. (eds.) WRAC 2002. LNCS (LNAI), vol. 2564, pp. 377\u2013390. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/978-3-540-45173-0_29"},{"key":"28_CR33","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/LRA.2015.2509024","volume":"1","author":"A Giusti","year":"2015","unstructured":"Giusti, A., et al.: A machine learning approach to visual perception of forest trails for mobile robots. IEEE Robot. Autom. Lett. 1, 661\u2013667 (2015)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Gordon, D., Kembhavi, A., Rastegari, M., Redmon, J., Fox, D., Farhadi, A.: IQA: visual Question Answering in Interactive Environments. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00430"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Gupta, A., Johnson, J., Fei-Fei, L., Savarese, S., Alahi, A.: Social GAN: socially acceptable trajectories with generative adversarial networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00240"},{"key":"28_CR36","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/978-3-319-71682-4_5","volume-title":"Autonomous Agents and Multiagent Systems","author":"JK Gupta","year":"2017","unstructured":"Gupta, J.K., Egorov, M., Kochenderfer, M.: Cooperative multi-agent control using deep reinforcement learning. In: Sukthankar, G., Rodriguez-Aguilar, J.A. (eds.) AAMAS 2017. LNCS (LNAI), vol. 10642, pp. 66\u201383. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-71682-4_5"},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"Henriques, J.F., Vedaldi, A.: MapNet: an allocentric spatial memory for mapping environments. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00884"},{"key":"28_CR38","unstructured":"Hill, F., Hermann, K.M., Blunsom, P., Clark, S.: Understanding grounded language learning agents. arXiv preprint arXiv:1710.09867 (2017)"},{"key":"28_CR39","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"28_CR40","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1126\/science.aau6249","volume":"364","author":"M Jaderberg","year":"2019","unstructured":"Jaderberg, M., et al.: Human-level performance in 3D multiplayer games with population-based reinforcement learning. Science 364, 859\u2013865 (2019)","journal-title":"Science"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Jain, U., et al.: Two body problem: collaborative visual task completion. In: CVPR (2019), first two authors contributed equally","DOI":"10.1109\/CVPR.2019.00685"},{"key":"28_CR42","unstructured":"Johnson, M., Hofmann, K., Hutton, T., Bignell, D.: The malmo platform for artificial intelligence experimentation. In: IJCAI (2016)"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Kahn, G., Zhang, T., Levine, S., Abbeel, P.: Plato: policy learning using adaptive trajectory optimization. In: ICRA (2017)","DOI":"10.1109\/ICRA.2017.7989379"},{"key":"28_CR44","doi-asserted-by":"crossref","unstructured":"Kasai, T., Tenmoto, H., Kamiya, A.: Learning of communication codes in multi-agent reinforcement learning problem. In: Proceedings of IEEE Soft Computing in Industrial Applications (2008)","DOI":"10.1109\/SMCIA.2008.5045926"},{"key":"28_CR45","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1109\/70.508439","volume":"12","author":"LE Kavraki","year":"1996","unstructured":"Kavraki, L.E., Svestka, P., Latombe, J.C., Overmars, M.H.: Probabilistic roadmaps for path planning in high-dimensional configuration spaces. IEEE Trans. Robot. Autom. 12, 566\u2013580 (1996)","journal-title":"IEEE Trans. Robot. Autom."},{"key":"28_CR46","doi-asserted-by":"crossref","unstructured":"Kempka, M., Wydmuch, M., Runc, G., Toczek, J., Jakowski, W.: ViZDoom: a doom-based AI research platform for visual reinforcement learning. In: Proceedings of IEEE Conference on Computational Intelligence and Games (2016)","DOI":"10.1109\/CIG.2016.7860433"},{"key":"28_CR47","unstructured":"Kolve, E., et al.: AI2-THOR: an interactive 3D environment for visual AI. arXiv preprint arXiv:1712.05474 (2019)"},{"key":"28_CR48","doi-asserted-by":"publisher","first-page":"941","DOI":"10.1177\/0278364910370376","volume":"29","author":"K Konolige","year":"2010","unstructured":"Konolige, K., et al.: View-based maps. Int. J. Robot. Res. 29, 941\u2013957 (2010)","journal-title":"Int. J. Robot. Res."},{"key":"28_CR49","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/0921-8890(91)90014-C","volume":"8","author":"B Kuipers","year":"1991","unstructured":"Kuipers, B., Byun, Y.T.: A robot exploration and mapping strategy based on a semantic hierarchy of spatial representations. Robot. Auton. Syst. 8, 47\u201363 (1991)","journal-title":"Robot. Auton. Syst."},{"key":"28_CR50","unstructured":"Lauer, M., Riedmiller, M.: An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In: ICML (2000)"},{"key":"28_CR51","unstructured":"Lavalle, S.M., Kuffner, J.J.: Rapidly-exploring random trees: progress and prospects. Algorithmic Comput. Robot.: New Direct (2000)"},{"key":"28_CR52","unstructured":"Lazaridou, A., Peysakhovich, A., Baroni, M.: Multi-agent cooperation and the emergence of (natural) language. In: arXiv preprint arXiv:1612.07182 (2016)"},{"key":"28_CR53","unstructured":"Lerer, A., Gross, S., Fergus, R.: Learning physical intuition of block towers by example. In: ICML (2016)"},{"key":"28_CR54","unstructured":"Liu, I.J., Yeh, R., Schwing, A.G.: PIC: permutation invariant critic for multi-agent deep reinforcement learning. In: CoRL (2019). First two authors contributed equally"},{"key":"28_CR55","doi-asserted-by":"crossref","unstructured":"Liu, Y.C., Tian, J., Glaser, N., Kira, Z.: When2com: multi-agent perception via communication graph grouping. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00416"},{"key":"28_CR56","doi-asserted-by":"crossref","unstructured":"Liu, Y.C., Tian, J., Ma, C.Y., Glaser, N., Kuo, C.W., Kira, Z.: Who2com: collaborative perception via learnable handshake communication. In: ICRA (2020)","DOI":"10.1109\/ICRA40945.2020.9197364"},{"key":"28_CR57","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: NeurIPS (2017)"},{"key":"28_CR58","doi-asserted-by":"crossref","unstructured":"Savva, M., et al.: Habitat: a platform for embodied AI research. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00943"},{"key":"28_CR59","doi-asserted-by":"crossref","unstructured":"Matignon, L., Laurent, G.J., Fort-Piat, N.L.: Hysteretic Q-learning: an algorithm for decentralized reinforcement learning in cooperative multi-agent teams. In: IROS (2007)","DOI":"10.1109\/IROS.2007.4399095"},{"key":"28_CR60","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/978-3-642-34799-3_13","volume-title":"Multi-Agent Systems","author":"FS Melo","year":"2012","unstructured":"Melo, F.S., Spaan, M.T.J., Witwicki, S.J.: QueryPOMDP: POMDP-based communication in multiagent systems. In: Cossentino, M., Kaisers, M., Tuyls, K., Weiss, G. (eds.) EUMAS 2011. LNCS (LNAI), vol. 7541, pp. 189\u2013204. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-34799-3_13"},{"key":"28_CR61","unstructured":"Mirowski, P., et al.: Learning to navigate in complex environments. In: ICLR (2017)"},{"key":"28_CR62","unstructured":"Mirowski, P., et al.: The streetlearn environment and dataset. arXiv preprint arXiv:1903.01292 (2019)"},{"key":"28_CR63","unstructured":"Mirowski, P., et al.: Learning to navigate in cities without a map. In: NeurIPS (2018)"},{"key":"28_CR64","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, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"28_CR65","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: ICML (2016)"},{"key":"28_CR66","doi-asserted-by":"crossref","unstructured":"Mordatch, I., Abbeel, P.: Emergence of grounded compositional language in multi-agent populations. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"28_CR67","unstructured":"Oh, J., Chockalingam, V., Singh, S., Lee, H.: Control of memory, active perception, and action in minecraft. In: ICML (2016)"},{"key":"28_CR68","unstructured":"Omidshafiei, S., Pazis, J., Amato, C., How, J.P., Vian, J.: Deep decentralized multi-task multi-agent reinforcement learning under partial observability. In: ICML (2017)"},{"key":"28_CR69","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. Autonom. Agents Multi-Agent Syst. AAMAS 11, 387\u2013434 (2005)","journal-title":"Autonom. Agents Multi-Agent Syst. AAMAS"},{"key":"28_CR70","unstructured":"Peng, P., et al.: Multiagent bidirectionally-coordinated nets: emergence of human-level coordination in learning to play starcraft combat games. arXiv preprint arXiv:1703.10069 (2017)"},{"key":"28_CR71","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1177\/027836498600500404","volume":"5","author":"RC Smith","year":"1986","unstructured":"Smith, R.C., Cheeseman, P.: On the representation and estimation of spatial uncertainty. Int. J. Robot. Res. 5, 56\u201368 (1986)","journal-title":"Int. J. Robot. Res."},{"key":"28_CR72","unstructured":"Ramakrishnan, S.K., Jayaraman, D., Grauman, K.: An exploration of embodied visual exploration. arXiv preprint arXiv:2001.02192 (2020)"},{"key":"28_CR73","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: ICML (2018)"},{"key":"28_CR74","unstructured":"Savinov, N., Dosovitskiy, A., Koltun, V.: Semi-parametric topological memory for navigation. In: ICLR (2018)"},{"key":"28_CR75","unstructured":"Savva, M., Chang, A.X., Dosovitskiy, A., Funkhouser, T., Koltun, V.: MINOS: multimodal indoor simulator for navigation in complex environments. arXiv preprint arXiv:1712.03931 (2017)"},{"key":"28_CR76","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"28_CR77","unstructured":"Smith, R.C., Self, M., Cheeseman, P.: Estimating uncertain spatial relationships in robotics. In: UAI (1986)"},{"key":"28_CR78","doi-asserted-by":"crossref","unstructured":"Suhr, A., et al.: Executing instructions in situated collaborative interactions. In: EMNLP (2019)","DOI":"10.18653\/v1\/D19-1218"},{"key":"28_CR79","unstructured":"Sukhbaatar, S., Szlam, A., Fergus, R.: Learning multiagent communication with backpropagation. In: NeurIPS (2016)"},{"key":"28_CR80","unstructured":"Sukhbaatar, S., Szlam, A., Synnaeve, G., Chintala, S., Fergus, R.: MazeBase: a sandbox for learning from games. arXiv preprint arXiv:1511.07401 (2015)"},{"key":"28_CR81","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"28_CR82","doi-asserted-by":"crossref","unstructured":"Tamar, A., Wu, Y., Thomas, G., Levine, S., Abbeel, P.: Value iteration networks. In: NeurIPS (2016)","DOI":"10.24963\/ijcai.2017\/700"},{"key":"28_CR83","doi-asserted-by":"publisher","first-page":"e0172395","DOI":"10.1371\/journal.pone.0172395","volume":"12","author":"A Tampuu","year":"2017","unstructured":"Tampuu, A., et al.: Multiagent cooperation and competition with deep reinforcement learning. PloS 12, e0172395 (2017)","journal-title":"PloS"},{"key":"28_CR84","doi-asserted-by":"crossref","unstructured":"Tan, M.: Multi-agent reinforcement learning: independent vs. cooperative agents. In: ICML (1993)","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"28_CR85","unstructured":"Tesauro, G.: Extending Q-learning to general adaptive multi-agent systems. In: NeurIPS (2004)"},{"key":"28_CR86","doi-asserted-by":"crossref","unstructured":"Thomason, J., Gordon, D., Bisk, Y.: Shifting the baseline: Single modality performance on visual navigation & QA. In: NAACL (2019)","DOI":"10.18653\/v1\/N19-1197"},{"key":"28_CR87","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/BF00129684","volume":"9","author":"C Tomasi","year":"1992","unstructured":"Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: a factorization method. IJCV 9, 137\u2013154 (1992)","journal-title":"IJCV"},{"key":"28_CR88","unstructured":"Toussaint, M.: Learning a world model and planning with a self-organizing, dynamic neural system. In: NeurIPS (2003)"},{"key":"28_CR89","unstructured":"Usunier, N., Synnaeve, G., Lin, Z., Chintala, S.: Episodic exploration for deep deterministic policies: an application to starcraft micromanagement tasks. In: ICLR (2016)"},{"key":"28_CR90","unstructured":"de Vries, H., Shuster, K., Batra, D., Parikh, D., Weston, J., Kiela, D.: Talk the walk: navigating new York city through grounded dialogue. arXiv preprint arXiv:1807.03367 (2018)"},{"key":"28_CR91","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00679"},{"key":"28_CR92","unstructured":"Weihs, L., Jain, U., Salvador, J., Lazebnik, S., Kembhavi, A., Schwing, A.: Bridging the imitation gap by adaptive insubordination. arXiv preprint arXiv:2007.12173 (2020). The first two authors contributed equally"},{"key":"28_CR93","unstructured":"Weihs, L., et al.: Artificial agents learn flexible visual representations by playing a hiding game. arXiv preprint arXiv:1912.08195 (2019)"},{"key":"28_CR94","unstructured":"Weihs, L., et al.: AllenAct: a framework for embodied AI research. arXiv (2020)"},{"key":"28_CR95","doi-asserted-by":"crossref","unstructured":"Wijmans, E., et al.: Embodied question answering in photorealistic environments with point cloud perception. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00682"},{"key":"28_CR96","doi-asserted-by":"crossref","unstructured":"Wortsman, M., Ehsani, K., Rastegari, M., Farhadi, A., Mottaghi, R.: Learning to learn how to learn: self-adaptive visual navigation using meta-learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00691"},{"key":"28_CR97","doi-asserted-by":"crossref","unstructured":"Wu, Y., Wu, Y., Tamar, A., Russell, S., Gkioxari, G., Tian, Y.: Bayesian relational memory for semantic visual navigation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00286"},{"key":"28_CR98","unstructured":"Wymann, B., Espi\u00e9, E., Guionneau, C., Dimitrakakis, C., Coulom, R., Sumner, A.: TORCS, the open racing car simulator (2013). http:\/\/www.torcs.org"},{"key":"28_CR99","unstructured":"Xia, F., et al.: Interactive Gibson: a benchmark for interactive navigation in cluttered environments. arXiv preprint arXiv:1910.14442 (2019)"},{"key":"28_CR100","doi-asserted-by":"crossref","unstructured":"Xia, F., Zamir, A.R., He, Z., Sax, A., Malik, J., Savarese, S.: Gibson ENv: real-world perception for embodied agents. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00945"},{"key":"28_CR101","unstructured":"Yang, J., Lu, J., Lee, S., Batra, D., Parikh, D.: Visual curiosity: learning to ask questions to learn visual recognition. In: CoRL (2018)"},{"key":"28_CR102","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Embodied amodal recognition: learning to move to perceive objects. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00213"},{"key":"28_CR103","unstructured":"Yang, W., Wang, X., Farhadi, A., Gupta, A., Mottaghi, R.: Visual semantic navigation using scene priors. In: ICLR (2018)"},{"key":"28_CR104","unstructured":"Zhang, K., Yang, Z., Ba\u015far, T.: Multi-agent reinforcement learning: a selective overview of theories and algorithms. arXiv preprint arXiv:1911.10635 (2019)"},{"key":"28_CR105","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Target-driven visual navigation in indoor scenes using deep reinforcement learning. In: ICRA (2017)","DOI":"10.1109\/ICRA.2017.7989381"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58558-7_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:54:40Z","timestamp":1730105680000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58558-7_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585570","9783030585587"],"references-count":105,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58558-7_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}