{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T18:24:09Z","timestamp":1778091849351,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":169,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T00:00:00Z","timestamp":1710115200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSF Graduate Research Fellowship"},{"name":"NSH Human-Centered Computing"},{"name":"Air Force Office of Scientific Research (AFOSR)"},{"name":"Open Philanthropy"},{"name":"Apple AI\/ML PhD Fellowship"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,11]]},"DOI":"10.1145\/3610977.3634987","type":"proceedings-article","created":{"date-parts":[[2024,3,10]],"date-time":"2024-03-10T00:19:00Z","timestamp":1710029940000},"page":"42-54","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Aligning Human and Robot Representations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9507-7427","authenticated-orcid":false,"given":"Andreea","family":"Bobu","sequence":"first","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8136-6175","authenticated-orcid":false,"given":"Andi","family":"Peng","sequence":"additional","affiliation":[{"name":"MIT, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9569-6690","authenticated-orcid":false,"given":"Pulkit","family":"Agrawal","sequence":"additional","affiliation":[{"name":"MIT, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1338-8107","authenticated-orcid":false,"given":"Julie A","family":"Shah","sequence":"additional","affiliation":[{"name":"MIT, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6312-5466","authenticated-orcid":false,"given":"Anca D.","family":"Dragan","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,3,11]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"International Conference on. ACM.","author":"Abbeel Pieter","year":"2004","unstructured":"Pieter Abbeel and Andrew Y Ng. 2004. Apprenticeship learning via inverse reinforcement learning. In Machine Learning (ICML), International Conference on. ACM."},{"key":"e_1_3_2_2_2_1","volume-title":"International Conference on Machine Learning. PMLR, 10--19","author":"Abel David","year":"2018","unstructured":"David Abel, Dilip Arumugam, Lucas Lehnert, and Michael Littman. 2018. State abstractions for lifelong reinforcement learning. In International Conference on Machine Learning. PMLR, 10--19."},{"key":"e_1_3_2_2_3_1","first-page":"7799","article-title":"On the expressivity of markov reward","volume":"34","author":"Abel David","year":"2021","unstructured":"David Abel, Will Dabney, Anna Harutyunyan, Mark K Ho, Michael Littman, Doina Precup, and Satinder Singh. 2021. On the expressivity of markov reward. Advances in Neural Information Processing Systems 34 (2021), 7799--7812.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_4_1","volume-title":"The Task Specification Problem. In Conference on Robot Learning. PMLR, 1745--1751","author":"Agrawal Pulkit","year":"2022","unstructured":"Pulkit Agrawal. 2022. The Task Specification Problem. In Conference on Robot Learning. PMLR, 1745--1751."},{"key":"e_1_3_2_2_5_1","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24--26, 2017, Workshop Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=HJ4-rAVtl","author":"Alain Guillaume","year":"2017","unstructured":"Guillaume Alain and Yoshua Bengio. 2017. Understanding intermediate layers using linear classifier probes. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24--26, 2017, Workshop Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=HJ4-rAVtl"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3023394"},{"key":"e_1_3_2_2_7_1","volume-title":"Concrete problems in AI safety. arXiv preprint arXiv:1606.06565","author":"Amodei Dario","year":"2016","unstructured":"Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, and Dan Man\u00e9. 2016. Concrete problems in AI safety. arXiv preprint arXiv:1606.06565 (2016)."},{"key":"e_1_3_2_2_8_1","volume-title":"Garnett (Eds.)","volume":"32","author":"Anand Ankesh","year":"2019","unstructured":"Ankesh Anand, Evan Racah, Sherjil Ozair, Yoshua Bengio, Marc-Alexandre C\u00f4t\u00e9, and R Devon Hjelm. 2019. Unsupervised State Representation Learning in Atari. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/ 6fb52e71b837628ac16539c1ff911667-Paper.pdf"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3524973"},{"key":"e_1_3_2_2_10_1","volume-title":"SHOP2: An HTN Planning System. CoRR abs\/1106.4869","author":"Au Tsz-Chiu","year":"2011","unstructured":"Tsz-Chiu Au, Okhtay Ilghami, Ugur Kuter, J. William Murdock, Dana S. Nau, Dan Wu, and Fusun Yaman. 2011. SHOP2: An HTN Planning System. CoRR abs\/1106.4869 (2011). arXiv:1106.4869 http:\/\/arxiv.org\/abs\/1106.4869"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327144.3327216"},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings of the 1st Annual Conference on Robot Learning (Proceedings of Machine Learning Research","volume":"226","author":"Bajcsy Andrea","unstructured":"Andrea Bajcsy, Dylan P. Losey, Marcia K. O'Malley, and Anca D. Dragan. 2017. Learning Robot Objectives from Physical Human Interaction. In Proceedings of the 1st Annual Conference on Robot Learning (Proceedings of Machine Learning Research, Vol. 78), Sergey Levine, Vincent Vanhoucke, and Ken Goldberg (Eds.). PMLR, 217--226. http:\/\/proceedings.mlr.press\/v78\/bajcsy17a.html"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2206.11795"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017016"},{"key":"e_1_3_2_2_15_1","unstructured":"Peter L. Bartlett Dylan J. Foster and Matus Telgarsky. 2017. Spectrallynormalized margin bounds for neural networks. In NIPS."},{"key":"e_1_3_2_2_16_1","volume-title":"Touretzky (Ed.)","volume":"1","author":"Baum Eric","year":"1988","unstructured":"Eric Baum and David Haussler. 1988. What Size Net Gives Valid Generalization?. In Advances in Neural Information Processing Systems, D. Touretzky (Ed.), Vol. 1. Morgan-Kaufmann. https:\/\/proceedings.neurips.cc\/paper\/1988\/ file\/1d7f7abc18fcb43975065399b0d1e48e-Paper.pdf"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17360"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019--11448--7"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"A. Bobu A. Bajcsy J. F. Fisac S. Deglurkar and A. D. Dragan. 2020. Quantifying Hypothesis Space Misspecification in Learning From Human--Robot Demonstrations and Physical Corrections. IEEE Transactions on Robotics (2020) 1--20.","DOI":"10.1109\/TRO.2020.2971415"},{"key":"e_1_3_2_2_20_1","volume-title":"Proceedings of The 2nd Conference on Robot Learning (Proceedings of Machine Learning Research","volume":"805","author":"Bobu Andreea","unstructured":"Andreea Bobu, Andrea Bajcsy, Jaime F. Fisac, and Anca D. Dragan. 2018. Learning under Misspecified Objective Spaces. In Proceedings of The 2nd Conference on Robot Learning (Proceedings of Machine Learning Research, Vol. 87), Aude Billard, Anca Dragan, Jan Peters, and Jun Morimoto (Eds.). PMLR, 796--805. http:\/\/proceedings.mlr.press\/v87\/bobu18a.html"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.00810"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","unstructured":"Andreea Bobu Chris Paxton Wei Yang Balakumar Sundaralingam Yu-Wei Chao Maya Cakmak and Dieter Fox. 2021. Learning Perceptual Concepts by Bootstrapping from Human Queries. https:\/\/doi.org\/10.48550\/ARXIV.2111. 05251","DOI":"10.48550\/ARXIV.2111"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3434073.3444667"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649221078031"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2021.06.018"},{"key":"e_1_3_2_2_26_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research","author":"Brown Daniel","year":"2020","unstructured":"Daniel Brown, Russell Coleman, Ravi Srinivasan, and Scott Niekum. 2020. Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 119), Hal Daum\u00e9 III and Aarti Singh (Eds.). PMLR, 1165--1177. http:\/\/proceedings.mlr.press\/v119\/brown20a.html"},{"key":"e_1_3_2_2_27_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461012"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157693"},{"key":"e_1_3_2_2_30_1","volume-title":"Fixation patterns in simple choice reflect optimal information sampling. PLoS computational biology 17, 3","author":"Callaway Frederick","year":"2021","unstructured":"Frederick Callaway, Antonio Rangel, and Thomas L Griffiths. 2021. Fixation patterns in simple choice reflect optimal information sampling. PLoS computational biology 17, 3 (2021), e1008863."},{"key":"e_1_3_2_2_31_1","volume-title":"4th Conference on Robot Learning, CoRL 2020","volume":"1581","author":"Chen Kevin","year":"2020","unstructured":"Kevin Chen, Nithin Shrivatsav Srikanth, David Kent, Harish Ravichandar, and Sonia Chernova. 2020. Learning Hierarchical Task Networks with Preferences from Unannotated Demonstrations. In 4th Conference on Robot Learning, CoRL 2020, 16--18 November 2020, Virtual Event \/ Cambridge, MA, USA (Proceedings of Machine Learning Research, Vol. 155), Jens Kober, Fabio Ramos, and Claire J. Tomlin (Eds.). PMLR, 1572--1581. https:\/\/proceedings.mlr.press\/v155\/chen21d. html"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/2540128.2540314"},{"key":"e_1_3_2_2_34_1","volume-title":"Garnett (Eds.)","volume":"30","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep Reinforcement Learning from Human Preferences. In Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc."},{"key":"e_1_3_2_2_35_1","volume-title":"A Bayesian Developmental Approach to Robotic Goal-Based Imitation Learning. PloS one 10 (11","author":"Jae-Yoon Chung Michael","year":"2015","unstructured":"Michael Jae-Yoon Chung, Abram Friesen, Dieter Fox, Andrew Meltzoff, and Rajesh Rao. 2015. A Bayesian Developmental Approach to Robotic Goal-Based Imitation Learning. PloS one 10 (11 2015), e0141965. https:\/\/doi.org\/10.1371\/ journal.pone.0141965"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Adam Coates and A. Ng. 2012. Learning Feature Representations with K-Means. In Neural Networks: Tricks of the Trade.","DOI":"10.1007\/978-3-642-35289-8_30"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3385655"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3056071"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.01836"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561782"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635890"},{"key":"e_1_3_2_2_42_1","volume-title":"Garnett (Eds.)","volume":"32","author":"de Haan Pim","year":"2019","unstructured":"Pim de Haan, Dinesh Jayaraman, and Sergey Levine. 2019. Causal Confusion in Imitation Learning. In Advances in Neural Information Processing Systems, H.Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_2_2_43_1","volume-title":"Causal Confusion in Imitation Learning. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"de Haan Pim","year":"2019","unstructured":"Pim de Haan, Dinesh Jayaraman, and Sergey Levine. 2019. Causal Confusion in Imitation Learning. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8--14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9-Buc, Emily B. Fox, and Roman Garnett (Eds.). 11693--11704. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/ 947018640bf36a2bb609d3557a285329-Abstract.html"},{"key":"e_1_3_2_2_44_1","volume-title":"Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence","author":"Anthony","year":"2005","unstructured":"Anthony M. Dearden and Yiannis Demiris. 2005. Learning Forward Models for Robots. In IJCAI-05, Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, Edinburgh, Scotland, UK, July 30 - August 5, 2005, Leslie Pack Kaelbling and Alessandro Saffiotti (Eds.). Professional Book Center, 1440--1445. http:\/\/ijcai.org\/Proceedings\/05\/Papers\/1329.pdf"},{"key":"e_1_3_2_2_45_1","volume-title":"Stefan Bauer, and Yoshua Bengio.","author":"Deleu Tristan","year":"2022","unstructured":"Tristan Deleu, Ant\u00f3nio G\u00f3is, Chris Emezue, Mansi Rankawat, Simon Lacoste- Julien, Stefan Bauer, and Yoshua Bengio. 2022. Bayesian Structure Learning with Generative Flow Networks. CoRR abs\/2202.13903 (2022). arXiv:2202.13903 https:\/\/arxiv.org\/abs\/2202.13903"},{"key":"e_1_3_2_2_46_1","unstructured":"Simon S. Du Wei Hu Sham M. Kakade Jason D. Lee and Qi Lei. 2020. Few-Shot Learning via Learning the Representation Provably. https:\/\/doi.org\/10.48550\/ ARXIV.2002.09434"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00537"},{"key":"e_1_3_2_2_48_1","volume-title":"Diversity is all you need: Learning skills without a reward function. arXiv preprint arXiv:1802.06070","author":"Eysenbach Benjamin","year":"2018","unstructured":"Benjamin Eysenbach, Abhishek Gupta, Julian Ibarz, and Sergey Levine. 2018. Diversity is all you need: Learning skills without a reward function. arXiv preprint arXiv:1802.06070 (2018)."},{"key":"e_1_3_2_2_49_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning -","volume":"70","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-Agnostic Meta- Learning for Fast Adaptation of Deep Networks. In Proceedings of the 34th International Conference on Machine Learning - Volume 70 (Sydney, NSW, Australia) (ICML'17). JMLR.org, 1126--1135."},{"key":"e_1_3_2_2_50_1","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning -","volume":"48","author":"Finn Chelsea","year":"2016","unstructured":"Chelsea Finn, Sergey Levine, and Pieter Abbeel. 2016. Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization. In Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48 (New York, NY, USA) (ICML'16). JMLR.org, 49--58."},{"key":"e_1_3_2_2_51_1","volume-title":"Yan Duan, Trevor Darrell, Sergey Levine, and Pieter Abbeel.","author":"Finn Chelsea","year":"2015","unstructured":"Chelsea Finn, Xin Yu Tan, Yan Duan, Trevor Darrell, Sergey Levine, and Pieter Abbeel. 2015. Learning Visual Feature Spaces for Robotic Manipulation with Deep Spatial Autoencoders. CoRR abs\/1509.06113 (2015). arXiv:1509.06113 http:\/\/arxiv.org\/abs\/1509.06113"},{"key":"e_1_3_2_2_52_1","volume-title":"Tomlin","author":"Fridovich-Keil David","year":"2019","unstructured":"David Fridovich-Keil, Andrea Bajcsy, Jaime F. Fisac, Sylvia L. Herbert, Steven Wang, Anca D. Dragan, and Claire J. Tomlin. 2019. Confidence-aware motion prediction for real-time collision avoidance. International Journal of Robotics Research (2019)."},{"key":"e_1_3_2_2_53_1","volume-title":"Learning Robust Rewards with Adverserial Inverse Reinforcement Learning. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rkHywl-A-","author":"Fu Justin","year":"2018","unstructured":"Justin Fu, Katie Luo, and Sergey Levine. 2018. Learning Robust Rewards with Adverserial Inverse Reinforcement Learning. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rkHywl-A-"},{"key":"e_1_3_2_2_54_1","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Fu Justin","year":"2018","unstructured":"Justin Fu, Avi Singh, Dibya Ghosh, Larry Yang, and Sergey Levine. 2018. Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (Montr\u00e9al, Canada) (NIPS'18). Curran Associates Inc., Red Hook, NY, USA, 8547--8556."},{"key":"e_1_3_2_2_55_1","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Fernando Fern\u00e1ndez Javier","year":"2015","unstructured":"Javier Garc?a and Fernando Fern\u00e1ndez. 2015. A comprehensive survey on safe reinforcement learning. Journal of Machine Learning Research 16, 1 (2015), 1437--1480.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_56_1","volume-title":"Learning Actionable Representations with Goal Conditioned Policies. In 7th International Conference on Learning Representations, ICLR 2019","author":"Ghosh Dibya","year":"2019","unstructured":"Dibya Ghosh, Abhishek Gupta, and Sergey Levine. 2019. Learning Actionable Representations with Goal Conditioned Policies. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6--9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=Hye9lnCct7"},{"key":"e_1_3_2_2_57_1","volume-title":"A Survey on Interpretable Reinforcement Learning. arXiv preprint arXiv:2112.13112","author":"Glanois Claire","year":"2021","unstructured":"Claire Glanois, Paul Weng, Matthieu Zimmer, Dong Li, Tianpei Yang, Jianye Hao, and Wulong Liu. 2021. A Survey on Interpretable Reinforcement Learning. arXiv preprint arXiv:2112.13112 (2021)."},{"key":"e_1_3_2_2_58_1","volume-title":"Multi-task maximum entropy inverse reinforcement learning. arXiv preprint arXiv:1805.08882","author":"Gleave Adam","year":"2018","unstructured":"Adam Gleave and Oliver Habryka. 2018. Multi-task maximum entropy inverse reinforcement learning. arXiv preprint arXiv:1805.08882 (2018)."},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015406"},{"key":"e_1_3_2_2_60_1","volume-title":"Proceedings of the 31st Conference On Learning Theory (Proceedings of Machine Learning Research","volume":"299","author":"Golowich Noah","year":"2018","unstructured":"Noah Golowich, Alexander Rakhlin, and Ohad Shamir. 2018. Size-Independent Sample Complexity of Neural Networks. In Proceedings of the 31st Conference On Learning Theory (Proceedings of Machine Learning Research, Vol. 75), S\u00e9bastien Bubeck, Vianney Perchet, and Philippe Rigollet (Eds.). PMLR, 297--299. https: \/\/proceedings.mlr.press\/v75\/golowich18a.html"},{"key":"e_1_3_2_2_61_1","volume-title":"International conference on machine learning. PMLR, 1792--1801","author":"Greydanus Samuel","year":"2018","unstructured":"Samuel Greydanus, Anurag Koul, Jonathan Dodge, and Alan Fern. 2018. Visualizing and understanding atari agents. In International conference on machine learning. PMLR, 1792--1801."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot"},{"key":"e_1_3_2_2_63_1","volume-title":"Explain your move: Understanding agent actions using focused feature saliency. arXiv preprint arXiv:1912.12191","author":"Gupta Piyush","year":"2019","unstructured":"Piyush Gupta, Nikaash Puri, Sukriti Verma, Sameer Singh, Dhruv Kayastha, Shripad Deshmukh, and Balaji Krishnamurthy. 2019. Explain your move: Understanding agent actions using focused feature saliency. arXiv preprint arXiv:1912.12191 (2019)."},{"key":"e_1_3_2_2_64_1","volume-title":"Garnett (Eds.)","volume":"31","author":"Ha David","year":"2018","unstructured":"David Ha and J\u00fcrgen Schmidhuber. 2018. Recurrent World Models Facilitate Policy Evolution. In Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.), Vol. 31. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2018\/file\/ 2de5d16682c3c35007e4e92982f1a2ba-Paper.pdf"},{"key":"e_1_3_2_2_65_1","volume-title":"Inverse reward design. Advances in neural information processing systems 30","author":"Hadfield-Menell Dylan","year":"2017","unstructured":"Dylan Hadfield-Menell, Smitha Milli, Pieter Abbeel, Stuart J Russell, and Anca Dragan. 2017. Inverse reward design. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_66_1","volume-title":"Garnett (Eds.)","volume":"30","author":"Hadfield-Menell Dylan","year":"2017","unstructured":"Dylan Hadfield-Menell, Smitha Milli, Pieter Abbeel, Stuart J Russell, and Anca Dragan. 2017. Inverse Reward Design. In Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc."},{"key":"e_1_3_2_2_67_1","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Hafner Danijar","year":"2020","unstructured":"Danijar Hafner, Timothy P. Lillicrap, Jimmy Ba, and Mohammad Norouzi. 2020. Dream to Control: Learning Behaviors by Latent Imagination. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26--30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id= S1lOTC4tDS"},{"key":"e_1_3_2_2_68_1","volume-title":"Proceedings of the 2017 Conference on Learning Theory (Proceedings of Machine Learning Research","volume":"1068","author":"Harvey Nick","year":"2017","unstructured":"Nick Harvey, Christopher Liaw, and Abbas Mehrabian. 2017. Nearly-tight VC-dimension bounds for piecewise linear neural networks. In Proceedings of the 2017 Conference on Learning Theory (Proceedings of Machine Learning Research, Vol. 65), Satyen Kale and Ohad Shamir (Eds.). PMLR, 1064--1068. https: \/\/proceedings.mlr.press\/v65\/harvey17a.html"},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487760"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/2909824.3020233"},{"key":"e_1_3_2_2_71_1","volume-title":"DARLA: Improving Zero-Shot Transfer in Reinforcement Learning. In ICML.","author":"Higgins Irina","year":"2017","unstructured":"Irina Higgins, Arka Pal, Andrei A. Rusu, Lo\u00efc Matthey, Christopher P. Burgess, Alexander Pritzel, Matthew M. Botvinick, Charles Blundell, and Alexander Lerchner. 2017. DARLA: Improving Zero-Shot Transfer in Reinforcement Learning. In ICML."},{"key":"e_1_3_2_2_72_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24","volume":"4238","author":"Hilgard Sophie","year":"2021","unstructured":"Sophie Hilgard, Nir Rosenfeld, Mahzarin R. Banaji, Jack Cao, and David C. Parkes. 2021. Learning Representations by Humans, for Humans. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 4227--4238. http:\/\/proceedings.mlr.press\/ v139\/hilgard21a.html"},{"key":"e_1_3_2_2_73_1","volume-title":"The value of abstraction. Current opinion in behavioral sciences 29","author":"Mark K Ho.","year":"2019","unstructured":"Mark K Ho. 2019. The value of abstraction. Current opinion in behavioral sciences 29 (2019)."},{"key":"e_1_3_2_2_74_1","volume-title":"3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings (Proceedings of Machine Learning Research","volume":"884","author":"Hristov Yordan","year":"2019","unstructured":"Yordan Hristov, Daniel Angelov, Michael Burke, Alex Lascarides, and Subramanian Ramamoorthy. 2019. Disentangled Relational Representations for Explaining and Learning from Demonstration. In 3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings (Proceedings of Machine Learning Research, Vol. 100), Leslie Pack Kaelbling, Danica Kragic, and Komei Sugiura (Eds.). PMLR, 870--884."},{"key":"e_1_3_2_2_75_1","volume-title":"Meta Preference Learning for Fast User Adaptation in Human-Supervisory Multi-Robot Deployments. In 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 5851--5856","author":"Huang Chao","year":"2021","unstructured":"Chao Huang, Wenhao Luo, and Rui Liu. 2021. Meta Preference Learning for Fast User Adaptation in Human-Supervisory Multi-Robot Deployments. In 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 5851--5856."},{"key":"e_1_3_2_2_76_1","volume-title":"Feature Dynamic Bayesian Networks. CoRR abs\/0812.4581","author":"Hutter Marcus","year":"2008","unstructured":"Marcus Hutter. 2008. Feature Dynamic Bayesian Networks. CoRR abs\/0812.4581 (2008). arXiv:0812.4581 http:\/\/arxiv.org\/abs\/0812.4581"},{"key":"e_1_3_2_2_77_1","volume-title":"Garnett (Eds.)","volume":"31","author":"Ibarz Borja","year":"2018","unstructured":"Borja Ibarz, Jan Leike, Tobias Pohlen, Geoffrey Irving, Shane Legg, and Dario Amodei. 2018. Reward learning from human preferences and demonstrations in Atari. In Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.), Vol. 31. Curran Associates, Inc., 8011--8023. https:\/\/proceedings.neurips.cc\/paper\/2018\/ file\/8cbe9ce23f42628c98f80fa0fac8b19a-Paper.pdf"},{"key":"e_1_3_2_2_78_1","volume-title":"Adversarial examples are not bugs, they are features. Advances in neural information processing systems 32","author":"Ilyas Andrew","year":"2019","unstructured":"Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, and Aleksander Madry. 2019. Adversarial examples are not bugs, they are features. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_2_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2000.895287"},{"key":"e_1_3_2_2_80_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-010--9212--1"},{"key":"e_1_3_2_2_81_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915581193"},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918776060"},{"key":"e_1_3_2_2_83_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1477"},{"key":"e_1_3_2_2_84_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-016--9601--1"},{"key":"e_1_3_2_2_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3171221.3171276"},{"key":"e_1_3_2_2_86_1","volume-title":"Contrastive Predictive Coding Based Feature for Automatic Speaker Verification. arXiv preprint arXiv:1904.01575","author":"Lai I","year":"2019","unstructured":"Cheng-I Lai. 2019. Contrastive Predictive Coding Based Feature for Automatic Speaker Verification. arXiv preprint arXiv:1904.01575 (2019)."},{"key":"e_1_3_2_2_87_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295387"},{"key":"e_1_3_2_2_88_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research","author":"Laskin Michael","year":"2020","unstructured":"Michael Laskin, Aravind Srinivas, and Pieter Abbeel. 2020. CURL: Contrastive Unsupervised Representations for Reinforcement Learning. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 119), Hal Daum\u00e9 III and Aarti Singh (Eds.). PMLR, 5639-- 5650. https:\/\/proceedings.mlr.press\/v119\/laskin20a.html"},{"key":"e_1_3_2_2_89_1","doi-asserted-by":"publisher","DOI":"10.1016\/j"},{"key":"e_1_3_2_2_90_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24","volume":"6163","author":"Lee Kimin","year":"2021","unstructured":"Kimin Lee, Laura M. Smith, and Pieter Abbeel. 2021. PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 6152-- 6163. http:\/\/proceedings.mlr.press\/v139\/lee21i.html"},{"key":"e_1_3_2_2_91_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"e_1_3_2_2_92_1","volume-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643","author":"Levine Sergey","year":"2020","unstructured":"Sergey Levine, Aviral Kumar, George Tucker, and Justin Fu. 2020. Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)."},{"key":"e_1_3_2_2_93_1","unstructured":"Sergey Levine Zoran Popovic and Vladlen Koltun. 2010. Feature construction for inverse reinforcement learning. In Advances in Neural Information Processing Systems. 1342--1350."},{"key":"e_1_3_2_2_94_1","doi-asserted-by":"publisher","DOI":"10.1145\/2589481"},{"key":"e_1_3_2_2_95_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Li Yunzhu","year":"2020","unstructured":"Yunzhu Li, Antonio Torralba, Anima Anandkumar, Dieter Fox, and Animesh Garg. 2020. Causal Discovery in Physical Systems from Videos. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6--12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/ 6822951732be44edf818dc5a97d32ca6-Abstract.html"},{"key":"e_1_3_2_2_96_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN"},{"key":"e_1_3_2_2_97_1","doi-asserted-by":"crossref","unstructured":"Weiyu Liu. 2022. A survey of semantic reasoning frameworks for robotic systems. (2022). http:\/\/weiyuliu.com\/data\/A_Survey_of_Semantic_Reasoning_ Frameworks_for_Robotic_Systems.pdf","DOI":"10.1016\/j.robot.2022.104294"},{"key":"e_1_3_2_2_98_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399517"},{"key":"e_1_3_2_2_99_1","volume-title":"Losey and Marcia Kilchenman O'Malley","author":"Dylan","year":"2018","unstructured":"Dylan P. Losey and Marcia Kilchenman O'Malley. 2018. Including Uncertainty when Learning from Human Corrections. In CoRL."},{"key":"e_1_3_2_2_100_1","volume-title":"Zemel","author":"Louizos Christos","year":"2016","unstructured":"Christos Louizos, Kevin Swersky, Yujia Li, Max Welling, and Richard S. Zemel. 2016. The Variational Fair Autoencoder. CoRR abs\/1511.00830 (2016)."},{"key":"e_1_3_2_2_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICARM.2019.8833723"},{"key":"e_1_3_2_2_102_1","volume-title":"3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings (Proceedings of Machine Learning Research","volume":"1132","author":"Lynch Corey","year":"2019","unstructured":"Corey Lynch, Mohi Khansari, Ted Xiao, Vikash Kumar, Jonathan Tompson, Sergey Levine, and Pierre Sermanet. 2019. Learning Latent Plans from Play. In 3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings (Proceedings of Machine Learning Research, Vol. 100), Leslie Pack Kaelbling, Danica Kragic, and Komei Sugiura (Eds.). PMLR, 1113--1132. http:\/\/proceedings.mlr.press\/v100\/lynch20a.html"},{"key":"e_1_3_2_2_103_1","unstructured":"Ashique Rupam Mahmood. 2011. Structure Learning of Causal Bayesian Networks: A Survey."},{"key":"e_1_3_2_2_104_1","volume-title":"On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning. arXiv preprint arXiv:2206.03271","author":"Mandi Zhao","year":"2022","unstructured":"Zhao Mandi, Pieter Abbeel, and Stephen James. 2022. On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning. arXiv preprint arXiv:2206.03271 (2022)."},{"key":"e_1_3_2_2_105_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390238"},{"key":"e_1_3_2_2_106_1","doi-asserted-by":"publisher","DOI":"10.1007\/3--540--36755--1_25"},{"key":"e_1_3_2_2_107_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9749-y"},{"key":"e_1_3_2_2_108_1","doi-asserted-by":"publisher","DOI":"10.1145\/2696454.2696474"},{"key":"e_1_3_2_2_109_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399511"},{"key":"e_1_3_2_2_110_1","volume-title":"Proceedings of the Twenty-Third International Conference (ICML 2006), Pittsburgh, Pennsylvania, USA, June 25- 29, 2006 (ACM International Conference Proceeding Series","volume":"672","author":"Nejati Negin","year":"2006","unstructured":"Negin Nejati, Pat Langley, and Tolga K\u00f6nik. 2006. Learning hierarchical task networks by observation. In Machine Learning, Proceedings of the Twenty-Third International Conference (ICML 2006), Pittsburgh, Pennsylvania, USA, June 25- 29, 2006 (ACM International Conference Proceeding Series, Vol. 148), William W. Cohen and Andrew W. Moore (Eds.). ACM, 665--672. https:\/\/doi.org\/10.1145\/ 1143844.1143928"},{"key":"e_1_3_2_2_111_1","doi-asserted-by":"publisher","DOI":"10.2460\/ajvr.67.2.323"},{"key":"e_1_3_2_2_112_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2483592"},{"key":"e_1_3_2_2_113_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197126"},{"key":"e_1_3_2_2_114_1","volume-title":"EngineKGI: Closed- Loop Knowledge Graph Inference. arXiv preprint arXiv:2112.01040","author":"Niu Guanglin","year":"2021","unstructured":"Guanglin Niu, Bo Li, Yongfei Zhang, and Shiliang Pu. 2021. EngineKGI: Closed- Loop Knowledge Graph Inference. arXiv preprint arXiv:2112.01040 (2021)."},{"key":"e_1_3_2_2_115_1","volume-title":"2nd Annual Conference on Robot Learning, CoRL 2018, Z\u00fcrich, Switzerland, 29--31 October 2018, Proceedings (Proceedings of Machine Learning Research","volume":"723","author":"Nyga Daniel","year":"2018","unstructured":"Daniel Nyga, Subhro Roy, Rohan Paul, Daehyung Park, Mihai Pomarlan, Michael Beetz, and Nicholas Roy. 2018. Grounding Robot Plans from Natural Language Instructions with Incomplete World Knowledge. In 2nd Annual Conference on Robot Learning, CoRL 2018, Z\u00fcrich, Switzerland, 29--31 October 2018, Proceedings (Proceedings of Machine Learning Research, Vol. 87). PMLR, 714--723. http: \/\/proceedings.mlr.press\/v87\/nyga18a.html"},{"key":"e_1_3_2_2_116_1","doi-asserted-by":"publisher","DOI":"10.1007\/11678823_6"},{"key":"e_1_3_2_2_117_1","doi-asserted-by":"publisher","DOI":"10.1561\/2300000053"},{"key":"e_1_3_2_2_118_1","volume-title":"Zero-Shot Visual Imitation. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2131--21313","author":"Pathak Deepak","year":"2018","unstructured":"Deepak Pathak, Parsa Mahmoudieh, Guanghao Luo, Pulkit Agrawal, Dian Chen, Fred Shentu, Evan Shelhamer, Jitendra Malik, Alexei A. Efros, and Trevor Darrell. 2018. Zero-Shot Visual Imitation. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2131--21313. https:\/\/doi. org\/10.1109\/CVPRW.2018.00278"},{"key":"e_1_3_2_2_119_1","volume-title":"Learning for Robot Decision Making under Distribution Shift: A Survey. arXiv preprint arXiv:2203.07558","author":"Paudel Abhishek","year":"2022","unstructured":"Abhishek Paudel. 2022. Learning for Robot Decision Making under Distribution Shift: A Survey. arXiv preprint arXiv:2203.07558 (2022)."},{"key":"e_1_3_2_2_120_1","volume-title":"Predicting Stable Configurations for Semantic Placement of Novel Objects. In Conference on Robot Learning (CoRL).","author":"Paxton Chris","year":"2021","unstructured":"Chris Paxton, Chris Xie, Tucker Hermans, and Dieter Fox. 2021. Predicting Stable Configurations for Semantic Placement of Novel Objects. In Conference on Robot Learning (CoRL). to appear."},{"key":"e_1_3_2_2_121_1","volume-title":"Causal Inference. In Causality: Objectives and Assessment (NIPS 2008 Workshop), Whistler, Canada, December 12, 2008 (JMLR Proceedings","volume":"58","author":"Pearl Judea","year":"2010","unstructured":"Judea Pearl. 2010. Causal Inference. In Causality: Objectives and Assessment (NIPS 2008 Workshop), Whistler, Canada, December 12, 2008 (JMLR Proceedings, Vol. 6), Isabelle Guyon, Dominik Janzing, and Bernhard Sch\u00f6lkopf (Eds.). JMLR.org, 39--58. http:\/\/proceedings.mlr.press\/v6\/pearl10a.html"},{"key":"e_1_3_2_2_122_1","volume-title":"Feedback, Adaptation: A Human-inthe- Loop Framework for Test-Time Policy Adaptation.","author":"Peng Andi","year":"2023","unstructured":"Andi Peng, Aviv Netanyahu, Mark K Ho, Tianmin Shu, Andreea Bobu, Julie Shah, and Pulkit Agrawal. 2023. Diagnosis, Feedback, Adaptation: A Human-inthe- Loop Framework for Test-Time Policy Adaptation. (2023)."},{"key":"e_1_3_2_2_123_1","volume-title":"International Conference on Machine Learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, JongWook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_124_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461076"},{"key":"e_1_3_2_2_125_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"e_1_3_2_2_126_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152707"},{"key":"e_1_3_2_2_127_1","volume-title":"International Conference on Machine Learning. PMLR, 8821--8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning. PMLR, 8821--8831."},{"key":"e_1_3_2_2_128_1","doi-asserted-by":"crossref","unstructured":"Nathan Ratliff David M Bradley Joel Chestnutt and J A Bagnell. 2007. Boosting structured prediction for imitation learning. In Advances in Neural Information Processing Systems. 1153--1160.","DOI":"10.7551\/mitpress\/7503.003.0149"},{"key":"e_1_3_2_2_129_1","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Reddy Siddharth","year":"2020","unstructured":"Siddharth Reddy, Anca D. Dragan, and Sergey Levine. 2020. SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26--30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=S1xKd24twB"},{"key":"e_1_3_2_2_130_1","volume-title":"Pragmatic Image Compression for Human-in-the-Loop Decision-Making. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Reddy Sid","year":"2021","unstructured":"Sid Reddy, Anca D. Dragan, and Sergey Levine. 2021. Pragmatic Image Compression for Human-in-the-Loop Decision-Making. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6--14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 26499--26510. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/ df0aab058ce179e4f7ab135ed4e641a9-Abstract.html"},{"key":"e_1_3_2_2_131_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13--18","volume":"8029","author":"Reddy Siddharth","year":"2020","unstructured":"Siddharth Reddy, Anca D. Dragan, Sergey Levine, Shane Legg, and Jan Leike. 2020. Learning Human Objectives by Evaluating Hypothetical Behavior. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13--18 July 2020, Virtual Event (Proceedings of Machine Learning Research, Vol. 119). PMLR, 8020--8029. http:\/\/proceedings.mlr.press\/v119\/reddy20a.html"},{"key":"e_1_3_2_2_132_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022"},{"key":"e_1_3_2_2_133_1","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 627--635","author":"Ross St\u00e9phane","year":"2011","unstructured":"St\u00e9phane Ross, Geoffrey Gordon, and Drew Bagnell. 2011. A reduction of imitation learning and structured prediction to no-regret online learning. In Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 627--635."},{"key":"e_1_3_2_2_134_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"e_1_3_2_2_135_1","volume-title":"Artificial intelligence a modern approach. Pearson Education","author":"Russell Stuart J","unstructured":"Stuart J Russell. 2010. Artificial intelligence a modern approach. Pearson Education, Inc."},{"key":"e_1_3_2_2_136_1","volume-title":"Workshop on Rich Representations for Reinforcement Learning. Citeseer, 57","author":"Sanner Scott","year":"2005","unstructured":"Scott Sanner. 2005. Simultaneous learning of structure and value in relational reinforcement learning. In Workshop on Rich Representations for Reinforcement Learning. Citeseer, 57."},{"key":"e_1_3_2_2_137_1","volume-title":"Dipendra Kumar Misra, and Hema Swetha Koppula","author":"Saxena Ashutosh","year":"2014","unstructured":"Ashutosh Saxena, Ashesh Jain, Ozan Sener, Aditya Jami, Dipendra Kumar Misra, and Hema Swetha Koppula. 2014. RoboBrain: Large-Scale Knowledge Engine for Robots. CoRR abs\/1412.0691 (2014). arXiv:1412.0691 http:\/\/arxiv.org\/abs\/ 1412.0691"},{"key":"e_1_3_2_2_138_1","volume-title":"Pretraining Representations for Data-Efficient Reinforcement Learning. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Schwarzer Max","year":"2021","unstructured":"Max Schwarzer, Nitarshan Rajkumar, Michael Noukhovitch, Ankesh Anand, Laurent Charlin, R. Devon Hjelm, Philip Bachman, and Aaron C. Courville. 2021. Pretraining Representations for Data-Efficient Reinforcement Learning. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6--14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 12686--12699. https:\/\/proceedings.neurips. cc\/paper\/2021\/hash\/69eba34671b3ef1ef38ee85caae6b2a1-Abstract.html"},{"key":"e_1_3_2_2_139_1","volume-title":"Shixiang Shane Gu, and Richard Zemel","author":"Seyed Ghasemipour Seyed Kamyar","year":"2019","unstructured":"Seyed Kamyar Seyed Ghasemipour, Shixiang Shane Gu, and Richard Zemel. 2019. Smile: Scalable meta inverse reinforcement learning through contextconditional policies. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_2_140_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/ forum?id=rkevMnRqYQ","author":"Shah Rohin","year":"2019","unstructured":"Rohin Shah, Dmitrii Krasheninnikov, Jordan Alexander, Pieter Abbeel, and Anca Dragan. 2019. The Implicit Preference Information in an Initial State. In International Conference on Learning Representations. https:\/\/openreview.net\/ forum?id=rkevMnRqYQ"},{"key":"e_1_3_2_2_141_1","volume-title":"Conference on Robot Learning. PMLR, 894--906","author":"Shridhar Mohit","year":"2022","unstructured":"Mohit Shridhar, Lucas Manuelli, and Dieter Fox. 2022. Cliport: What and where pathways for robotic manipulation. In Conference on Robot Learning. PMLR, 894--906."},{"key":"e_1_3_2_2_142_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197020"},{"key":"e_1_3_2_2_143_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.073"},{"key":"e_1_3_2_2_144_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5979666"},{"key":"e_1_3_2_2_145_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5649406"},{"key":"e_1_3_2_2_146_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2203.02091"},{"key":"e_1_3_2_2_147_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24","volume":"9879","author":"Stooke Adam","year":"2021","unstructured":"Adam Stooke, Kimin Lee, Pieter Abbeel, and Michael Laskin. 2021. Decoupling Representation Learning from Reinforcement Learning. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 9870--9879. http:\/\/proceedings.mlr.press\/v139\/ stooke21a.html"},{"key":"e_1_3_2_2_148_1","volume-title":"Dragan","author":"Sun Liting","year":"2021","unstructured":"Liting Sun, Xiaogang Jia, and Anca D. Dragan. 2021. On complementing end-toend human behavior predictors with planning. Robotics: Science and Systems XVII (2021)."},{"key":"e_1_3_2_2_149_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"e_1_3_2_2_150_1","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2022.2083463"},{"key":"e_1_3_2_2_151_1","volume-title":"Representation Learning with Contrastive Predictive Coding. CoRR abs\/1807.03748","author":"van den Oord A\u00e4ron","year":"2018","unstructured":"A\u00e4ron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation Learning with Contrastive Predictive Coding. CoRR abs\/1807.03748 (2018). arXiv:1807.03748 http:\/\/arxiv.org\/abs\/1807.03748"},{"key":"e_1_3_2_2_152_1","unstructured":"Paul Vernaza and Drew Bagnell. 2012. Efficient high dimensional maximum entropy modeling via symmetric partition functions. In Advances in Neural Information Processing Systems. 575--583."},{"key":"e_1_3_2_2_153_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2754499"},{"key":"e_1_3_2_2_154_1","volume-title":"Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces. ArXiv abs\/1709.10163","author":"Warnell Garrett","year":"2018","unstructured":"Garrett Warnell, Nicholas R. Waytowich, Vernon J. Lawhern, and Peter Stone. 2018. Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces. ArXiv abs\/1709.10163 (2018)."},{"key":"e_1_3_2_2_155_1","volume-title":"Garnett (Eds.)","volume":"28","author":"Watter Manuel","year":"2015","unstructured":"Manuel Watter, Jost Springenberg, Joschka Boedecker, and Martin Riedmiller. 2015. Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images. In Advances in Neural Information Processing Systems, C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett (Eds.), Vol. 28. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2015\/"},{"key":"e_1_3_2_2_156_1","volume-title":"2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 2089--2095","author":"Wulfmeier M.","unstructured":"M.Wulfmeier, D. Z.Wang, and I. Posner. 2016.Watch this: Scalable cost-function learning for path planning in urban environments. In 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 2089--2095."},{"key":"e_1_3_2_2_157_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331203"},{"key":"e_1_3_2_2_158_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"6962","author":"Xu Kelvin","year":"2019","unstructured":"Kelvin Xu, Ellis Ratner, Anca Dragan, Sergey Levine, and Chelsea Finn. 2019. Learning a Prior over Intent via Meta-Inverse Reinforcement Learning. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 6952--6962. https:\/\/proceedings.mlr.press\/v97\/xu19d.html"},{"key":"e_1_3_2_2_159_1","volume-title":"Task-Induced Representation Learning. In The Tenth International Conference on Learning Representations, ICLR 2022","author":"Yamada Jun","year":"2022","unstructured":"Jun Yamada, Karl Pertsch, Anisha Gunjal, and Joseph J. Lim. 2022. Task-Induced Representation Learning. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25--29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=OzyXtIZAzFv"},{"key":"e_1_3_2_2_160_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24","volume":"11794","author":"Yang Mengjiao","year":"2021","unstructured":"Mengjiao Yang and Ofir Nachum. 2021. Representation Matters: Offline Pretraining for Sequential Decision Making. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 11784--11794. http:\/\/proceedings.mlr.press\/v139\/yang21h.html"},{"key":"e_1_3_2_2_161_1","volume-title":"Incremental Object Grounding Using Scene Graphs. CoRR abs\/2201.01901","author":"Keun Yi John Seon","year":"2022","unstructured":"John Seon Keun Yi, Yoonwoo Kim, and Sonia Chernova. 2022. Incremental Object Grounding Using Scene Graphs. CoRR abs\/2201.01901 (2022). arXiv:2201.01901 https:\/\/arxiv.org\/abs\/2201.01901"},{"key":"e_1_3_2_2_162_1","volume-title":"Meta-inverse reinforcement learning with probabilistic context variables. Advances in Neural Information Processing Systems 32","author":"Yu Lantao","year":"2019","unstructured":"Lantao Yu, Tianhe Yu, Chelsea Finn, and Stefano Ermon. 2019. Meta-inverse reinforcement learning with probabilistic context variables. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_2_163_1","volume-title":"SORNet: Spatial Object-Centric Representations for Sequential Manipulation. In 5th Annual Conference on Robot Learning. PMLR, 148--157","author":"Yuan Wentao","year":"2021","unstructured":"Wentao Yuan, Chris Paxton, Karthik Desingh, and Dieter Fox. 2021. SORNet: Spatial Object-Centric Representations for Sequential Manipulation. In 5th Annual Conference on Robot Learning. PMLR, 148--157."},{"key":"e_1_3_2_2_164_1","volume-title":"Proceedings, Part XXIII (Lecture Notes in Computer Science","volume":"623","author":"Zareian Alireza","year":"2020","unstructured":"Alireza Zareian, Svebor Karaman, and Shih-Fu Chang. 2020. Bridging Knowledge Graphs to Generate Scene Graphs. In Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXIII (Lecture Notes in Computer Science, Vol. 12368), Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.). Springer, 606--623. https:\/\/doi. org\/10.1007\/978--3-030--58592--1_36"},{"key":"e_1_3_2_2_165_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Zhang Amy","year":"2021","unstructured":"Amy Zhang, Rowan Thomas McAllister, Roberto Calandra, Yarin Gal, and Sergey Levine. 2021. Learning Invariant Representations for Reinforcement Learning without Reconstruction. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=-2FCwDKRREu"},{"key":"e_1_3_2_2_166_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"e_1_3_2_2_167_1","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/7588221"},{"key":"e_1_3_2_2_168_1","volume-title":"Proceedings of the 23rd National Conference on Artificial Intelligence -","volume":"3","author":"Ziebart Brian D.","year":"2027","unstructured":"Brian D. Ziebart, Andrew Maas, J. Andrew Bagnell, and Anind K. Dey. 2008. Maximum Entropy Inverse Reinforcement Learning. In Proceedings of the 23rd National Conference on Artificial Intelligence - Volume 3 (Chicago, Illinois) (AAAI'08). AAAI Press, 1433--1438. http:\/\/dl.acm.org\/citation.cfm?id=1620270.1620297"},{"key":"e_1_3_2_2_169_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561839"}],"event":{"name":"HRI '24: ACM\/IEEE International Conference on Human-Robot Interaction","location":"Boulder CO USA","acronym":"HRI '24","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2024 ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610977.3634987","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3610977.3634987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T16:36:01Z","timestamp":1756398961000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610977.3634987"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,11]]},"references-count":169,"alternative-id":["10.1145\/3610977.3634987","10.1145\/3610977"],"URL":"https:\/\/doi.org\/10.1145\/3610977.3634987","relation":{},"subject":[],"published":{"date-parts":[[2024,3,11]]},"assertion":[{"value":"2024-03-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}