{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T21:28:44Z","timestamp":1793741324388,"version":"4.6.1"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/tdmrep.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197468","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T17:25:46Z","timestamp":1600190746000},"page":"4051-4058","source":"Crossref","is-referenced-by-count":50,"title":["Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Richard","family":"Li","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Allan","family":"Jabri","sequence":"additional","affiliation":[{"name":"University of California Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[{"name":"University of California Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pulkit","family":"Agrawal","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Structural-rnn: Deep learning on spatio-temporal graphs","author":"jain","year":"2015","journal-title":"CoRR"},{"key":"ref38","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007694015589"},{"key":"ref32","first-page":"31","article-title":"Learning in worlds with objects","author":"kaelbling","year":"2001","journal-title":"Working Notes of the AAAI Stanford Spring Symposium on Learning Grounded Representations"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref37","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume":"29","author":"defferrard","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref36","article-title":"Spectral networks and locally connected networks on graphs","author":"bruna","year":"2014","journal-title":"International Conference on Learning Representations (ICLR2014) CBLS April 2014"},{"key":"ref35","author":"russell","year":"2009","journal-title":"Artificial Intelligence A Modern Approach"},{"key":"ref34","article-title":"Relational representations in reinforcement learning: Review and open problems","volume":"2","author":"van otterlo","year":"2002","journal-title":"Proceedings of the ICML"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref62","first-page":"1312","article-title":"Universal value function approximators","author":"schaul","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref61","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref63","first-page":"5048","article-title":"Hindsight experience replay","volume":"30","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"On first-order meta-learning algorithms","author":"nichol","year":"2018"},{"key":"ref64","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"ICLRE"},{"key":"ref27","article-title":"Illuminating generalization in deep reinforcement learning through procedural level generation","author":"justesen","year":"2018"},{"key":"ref29","article-title":"Divide-and-conquer reinforcement learning","author":"ghosh","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.008"},{"key":"ref1","first-page":"6765","article-title":"Inverse reward design","author":"hadfield-menell","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Nervenet: Learning structured policy with graph neural networks","author":"wang","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref22","first-page":"647","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref21","article-title":"Learning to control self- assembling morphologies: A study of generalization via modularity","author":"pathak","year":"2019"},{"key":"ref24","first-page":"91","article-title":"Faster r-cnn: Towards realtime object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","author":"agrawal","year":"2016","journal-title":"NIPS"},{"key":"ref26","article-title":"Quantifying generalization in reinforcement learning","author":"cobbe","year":"2018"},{"key":"ref25","article-title":"A study on overfitting in deep reinforcement learning","author":"zhang","year":"2018"},{"key":"ref50","first-page":"1087","article-title":"One-shot imitation learning","author":"duan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref51","article-title":"Data-efficient deep reinforcement learning for dexterous manipulation","author":"popov","year":"2018"},{"key":"ref59","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018"},{"key":"ref58","article-title":"Modulated policy hierarchies","author":"pashevich","year":"2018","journal-title":"CoRR"},{"key":"ref57","article-title":"The option-critic architecture","author":"bacon","year":"2016","journal-title":"CoRR"},{"key":"ref56","first-page":"118","article-title":"The maxq method for hierarchical reinforcement learning","author":"dietterich","year":"1998","journal-title":"Proceedings of the Fifteenth International Conference on Machine Learning"},{"key":"ref55","first-page":"271278","article-title":"Feudal reinforcement learning","author":"dayan","year":"1993","journal-title":"Advances in neural information processing systems"},{"key":"ref54","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"2017","journal-title":"CoRR"},{"key":"ref53","article-title":"Logic-geometric programming: An optimization-based approach to combined task and motion planning","author":"toussaint","year":"2015","journal-title":"Twenty-Fourth International Joint Conference on Artificial Intelligence"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9651-z"},{"key":"ref10","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"CoRR"},{"key":"ref11","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref40","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"CoRR"},{"key":"ref12","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2016","journal-title":"JMLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2056368"},{"key":"ref15","article-title":"Exploration in model-based reinforcement learning by empirically estimating learning progress","author":"lopes","year":"2012","journal-title":"NIPS"},{"key":"ref16","article-title":"What is intrinsic motivation? a typology of computational approaches","author":"oudeyer","year":"2009","journal-title":"Frontiers in Neurorobotics"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref18","article-title":"Intrinsic motivation and automatic curricula via asymmetric self-play","author":"sukhbaatar","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref19","article-title":"Deep reinforcement learning with relational inductive biases","author":"zambaldi","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref4","article-title":"Overcoming exploration in reinforcement learning with demonstrations","author":"nair","year":"2017","journal-title":"CoRR"},{"key":"ref3","article-title":"Progressive neural networks","author":"rusu","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5649089"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref8","article-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations","author":"rajeswaran","year":"2017"},{"key":"ref7","article-title":"Learning dexterous in-hand manipulation","author":"andrychowicz","year":"2018"},{"key":"ref49","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"2017"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11796","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref46","article-title":"Learning to execute","author":"zaremba","year":"2014","journal-title":"CoRR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref48","article-title":"Automatic goal generation for reinforcement learning agents","author":"held","year":"2017","journal-title":"CoRR"},{"key":"ref47","article-title":"Automated curriculum learning for neural networks","author":"graves","year":"2017","journal-title":"CoRR"},{"key":"ref42","first-page":"1087","article-title":"One-shot imitation learning","volume":"30","author":"duan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref41","first-page":"4509","article-title":"Interaction networks for learning about objects, relations and physics","author":"battaglia","year":"0"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"ref43","article-title":"Reasoning about physical interactions with object-oriented prediction and planning","author":"janner","year":"2019","journal-title":"International Conference on Learning Representations"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197468.pdf?arnumber=9197468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T20:33:09Z","timestamp":1793737989000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197468","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}