{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:21:55Z","timestamp":1750220515494,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,11,10]],"date-time":"2021-11-10T00:00:00Z","timestamp":1636502400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Leonhard Obermeyer Center"},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1955404,IIS-1703883,IIS-1955365,RETTL-2119265,EAGER-2122119"],"award-info":[{"award-number":["IIS-1955404,IIS-1703883,IIS-1955365,RETTL-2119265,EAGER-2122119"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11,10]]},"DOI":"10.1145\/3487983.3488292","type":"proceedings-article","created":{"date-parts":[[2021,11,5]],"date-time":"2021-11-05T04:09:26Z","timestamp":1636085366000},"page":"1-11","source":"Crossref","is-referenced-by-count":1,"title":["SNAP:Successor Entropy based Incremental Subgoal Discovery for Adaptive Navigation"],"prefix":"10.1145","author":[{"given":"Rohit K.","family":"Dubey","sequence":"first","affiliation":[{"name":"Technical University of Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel S.","family":"Sohn","sequence":"additional","affiliation":[{"name":"Rutgers University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jimmy","family":"Abualdenien","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tyler","family":"Thrash","sequence":"additional","affiliation":[{"name":"Saint Louis University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Hoelscher","sequence":"additional","affiliation":[{"name":"ETH Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andr\u00e9","family":"Borrmann","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mubbasir","family":"Kapadia","sequence":"additional","affiliation":[{"name":"Rutgers University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,11,10]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Marcin Andrychowicz Filip Wolski Alex Ray Jonas Schneider Rachel Fong Peter Welinder Bob McGrew Josh Tobin Pieter Abbeel and Wojciech Zaremba. 2017. Hindsight experience replay. arXiv preprint arXiv:1707.01495(2017).  Marcin Andrychowicz Filip Wolski Alex Ray Jonas Schneider Rachel Fong Peter Welinder Bob McGrew Josh Tobin Pieter Abbeel and Wojciech Zaremba. 2017. Hindsight experience replay. arXiv preprint arXiv:1707.01495(2017)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1515\/REVNEURO.2006.17.1-2.71"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.5840\/philstudies19802725"},{"volume-title":"Proceedings of the annual meeting of the cognitive science society, Vol.\u00a031","year":"2009","author":"Buecher J","key":"e_1_3_2_2_5_1"},{"volume-title":"What do grid cells contribute to place cell firing?Trends in neurosciences 37, 3","year":"2014","author":"Bush Daniel","key":"e_1_3_2_2_6_1"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2015.07.006"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.4.613"},{"key":"e_1_3_2_2_9_1","first-page":"1","article-title":"Identifying indoor navigation landmarks using a hierarchical multi-criteria decision framework","author":"Dubey K","year":"2019","journal-title":"Motion, Interaction and Games."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.7551\/978-0-262-33027-5-ch039"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1162\/isal_a_00053"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/hipo.23147"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2012.0533"},{"key":"e_1_3_2_2_14_1","unstructured":"Benjamin Eysenbach Ruslan Salakhutdinov and Sergey Levine. 2019. Search on the replay buffer: Bridging planning and reinforcement learning. arXiv preprint arXiv:1906.05253(2019).  Benjamin Eysenbach Ruslan Salakhutdinov and Sergey Levine. 2019. Search on the replay buffer: Bridging planning and reinforcement learning. arXiv preprint arXiv:1906.05253(2019)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.5684-07.2008"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0151-18.2018"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature03721"},{"volume-title":"The Termination Critic. In The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 2231\u20132240","year":"2019","author":"Harutyunyan Anna","key":"e_1_3_2_2_18_1"},{"key":"e_1_3_2_2_19_1","first-page":"1942","article-title":"Mapping state space using landmarks for universal goal reaching","volume":"32","author":"Huang Zhiao","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Proceedings of the tenth international conference on machine learning, Vol.\u00a0951","year":"1993","author":"Kaelbling Leslie\u00a0Pack","key":"e_1_3_2_2_20_1"},{"key":"e_1_3_2_2_21_1","unstructured":"Tejas\u00a0D Kulkarni Karthik\u00a0R Narasimhan Ardavan Saeedi and Joshua\u00a0B Tenenbaum. 2016. Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation. arXiv preprint arXiv:1604.06057(2016).  Tejas\u00a0D Kulkarni Karthik\u00a0R Narasimhan Ardavan Saeedi and Joshua\u00a0B Tenenbaum. 2016. Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation. arXiv preprint arXiv:1604.06057(2016)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.1319-09.2009"},{"volume-title":"International Conference on Machine Learning. PMLR, 2295\u20132304","year":"2017","author":"Machado C","key":"e_1_3_2_2_23_1"},{"key":"e_1_3_2_2_24_1","unstructured":"Marlos\u00a0C Machado Clemens Rosenbaum Xiaoxiao Guo Miao Liu Gerald Tesauro and Murray Campbell. 2017b. Eigenoption discovery through the deep successor representation. arXiv preprint arXiv:1710.11089(2017).  Marlos\u00a0C Machado Clemens Rosenbaum Xiaoxiao Guo Miao Liu Gerald Tesauro and Murray Campbell. 2017b. Eigenoption discovery through the deep successor representation. arXiv preprint arXiv:1710.11089(2017)."},{"key":"e_1_3_2_2_25_1","unstructured":"Amy McGovern and Andrew\u00a0G Barto. 2001. Automatic discovery of subgoals in reinforcement learning using diverse density. (2001).  Amy McGovern and Andrew\u00a0G Barto. 2001. Automatic discovery of subgoals in reinforcement learning using diverse density. (2001)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1932"},{"volume-title":"European Conference on Machine Learning. Springer, 295\u2013306","year":"2002","author":"Menache Ishai","key":"e_1_3_2_2_27_1"},{"key":"e_1_3_2_2_28_1","unstructured":"Piotr Mirowski Razvan Pascanu Fabio Viola Hubert Soyer Andrew\u00a0J Ballard Andrea Banino Misha Denil Ross Goroshin Laurent Sifre Koray Kavukcuoglu 2016. Learning to navigate in complex environments. arXiv preprint arXiv:1611.03673(2016).  Piotr Mirowski Razvan Pascanu Fabio Viola Hubert Soyer Andrew\u00a0J Ballard Andrea Banino Misha Denil Ross Goroshin Laurent Sifre Koray Kavukcuoglu 2016. Learning to navigate in complex environments. arXiv preprint arXiv:1611.03673(2016)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-017-0180-8"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17604-3_6"},{"key":"e_1_3_2_2_31_1","unstructured":"Ofir Nachum Shixiang Gu Honglak Lee and Sergey Levine. 2018. Data-efficient hierarchical reinforcement learning. arXiv preprint arXiv:1805.08296(2018).  Ofir Nachum Shixiang Gu Honglak Lee and Sergey Levine. 2018. Data-efficient hierarchical reinforcement learning. arXiv preprint arXiv:1805.08296(2018)."},{"key":"e_1_3_2_2_32_1","unstructured":"Ashvin Nair Vitchyr Pong Murtaza Dalal Shikhar Bahl Steven Lin and Sergey Levine. 2018. Visual reinforcement learning with imagined goals. arXiv preprint arXiv:1807.04742(2018).  Ashvin Nair Vitchyr Pong Murtaza Dalal Shikhar Bahl Steven Lin and Sergey Levine. 2018. Visual reinforcement learning with imagined goals. arXiv preprint arXiv:1807.04742(2018)."},{"key":"e_1_3_2_2_33_1","unstructured":"Soroush Nasiriany Vitchyr\u00a0H Pong Steven Lin and Sergey Levine. 2019. Planning with goal-conditioned policies. arXiv preprint arXiv:1911.08453(2019).  Soroush Nasiriany Vitchyr\u00a0H Pong Steven Lin and Sergey Levine. 2019. Planning with goal-conditioned policies. arXiv preprint arXiv:1911.08453(2019)."},{"volume-title":"The hippocampus as a spatial map: Preliminary evidence from unit activity in the freely-moving rat.Brain research","year":"1971","author":"O\u2019Keefe John","key":"e_1_3_2_2_34_1"},{"key":"e_1_3_2_2_35_1","unstructured":"Vitchyr Pong Shixiang Gu Murtaza Dalal and Sergey Levine. 2018. Temporal difference models: Model-free deep rl for model-based control. arXiv preprint arXiv:1802.09081(2018).  Vitchyr Pong Shixiang Gu Murtaza Dalal and Sergey Levine. 2018. Temporal difference models: Model-free deep rl for model-based control. arXiv preprint arXiv:1802.09081(2018)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Rahul Ramesh Manan Tomar and Balaraman Ravindran. 2019. Successor options: An option discovery framework for reinforcement learning. arXiv preprint arXiv:1905.05731(2019).  Rahul Ramesh Manan Tomar and Balaraman Ravindran. 2019. Successor options: An option discovery framework for reinforcement learning. arXiv preprint arXiv:1905.05731(2019).","DOI":"10.24963\/ijcai.2019\/458"},{"volume-title":"Predictive representations can link model-based reinforcement learning to model-free mechanisms. PLoS computational biology 13, 9","year":"2017","author":"Russek M","key":"e_1_3_2_2_37_1"},{"volume-title":"International conference on machine learning. PMLR, 1312\u20131320","year":"2015","author":"Schaul Tom","key":"e_1_3_2_2_38_1"},{"key":"e_1_3_2_2_39_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347(2017).  John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347(2017)."},{"volume-title":"Mice learn multi-step routes by memorizing subgoal locations. BioRxiv","year":"2020","author":"Shamash Philip","key":"e_1_3_2_2_40_1"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015353"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1166466"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1002\/hipo.20244"},{"volume-title":"The hippocampus as a predictive map. Nature neuroscience 20, 11","year":"2017","author":"Stachenfeld L","key":"e_1_3_2_2_44_1"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.05913"},{"volume-title":"International Symposium on abstraction, reformulation, and approximation. Springer, 212\u2013223","year":"2002","author":"Stolle Martin","key":"e_1_3_2_2_46_1"},{"volume-title":"Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial intelligence 112, 1-2","year":"1999","author":"Sutton S","key":"e_1_3_2_2_47_1"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.10-02-00420.1990"},{"key":"e_1_3_2_2_49_1","unstructured":"Abhishek Verma and B\u00e9r\u00e9nice Mettler. 2017. Human learning of unknown environments in agile guidance tasks. arXiv preprint arXiv:1710.07757(2017).  Abhishek Verma and B\u00e9r\u00e9nice Mettler. 2017. Human learning of unknown environments in agile guidance tasks. arXiv preprint arXiv:1710.07757(2017)."},{"key":"e_1_3_2_2_50_1","unstructured":"Chengguang Xu Christopher Amato and Lawson\u00a0LS Wong. 2021. Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps. arXiv preprint arXiv:2106.03665(2021).  Chengguang Xu Christopher Amato and Lawson\u00a0LS Wong. 2021. Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps. arXiv preprint arXiv:2106.03665(2021)."},{"key":"e_1_3_2_2_51_1","unstructured":"Lunjun Zhang Ge Yang and Bradly\u00a0C Stadie. 2020. World Model as a Graph: Learning Latent Landmarks for Planning. arXiv preprint arXiv:2011.12491(2020).  Lunjun Zhang Ge Yang and Bradly\u00a0C Stadie. 2020. World Model as a Graph: Learning Latent Landmarks for Planning. arXiv preprint arXiv:2011.12491(2020)."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"}],"event":{"name":"MIG '21: Motion, Interaction and Games","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"],"location":"Virtual Event Switzerland","acronym":"MIG '21"},"container-title":["Motion, Interaction and Games"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3487983.3488292","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3487983.3488292","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3487983.3488292","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3487983.3488292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:24:32Z","timestamp":1750195472000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3487983.3488292"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,10]]},"references-count":51,"alternative-id":["10.1145\/3487983.3488292","10.1145\/3487983"],"URL":"https:\/\/doi.org\/10.1145\/3487983.3488292","relation":{},"subject":[],"published":{"date-parts":[[2021,11,10]]}}}