{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T17:51:31Z","timestamp":1789235491673,"version":"build-2803163510"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8]]},"abstract":"<jats:p>Learning how to execute complex tasks involving multiple objects in a 3D world is challenging when there is no ground-truth information about the objects or any demonstration to learn from.\n\nWhen an agent only receives a signal from task-completion, this makes it challenging to learn the object-representations which support learning the correct object-interactions needed to complete the task.\n\nIn this work, we formulate learning an attentive object dynamics model as a classification problem, using random object-images to define incorrect labels for our object-dynamics model.\n\nWe show empirically that this enables object-representation learning that captures an object's category (is it a toaster?), its properties (is it on?), and object-relations (is something inside of it?).\n\nWith this, our core learner (a relational RL agent) receives the dense training signal it needs to rapidly learn object-interaction tasks.\n\nWe demonstrate results in the 3D AI2Thor simulated kitchen environment with a range of challenging food preparation tasks.\n\nWe compare our method's performance to several related approaches and against the performance of an oracle: an agent that is supplied with ground-truth information about objects in the scene.\n\nWe find that our agent achieves performance closest to the oracle in terms of both learning speed and maximum success rate.<\/jats:p>","DOI":"10.24963\/ijcai.2021\/306","type":"proceedings-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T11:00:49Z","timestamp":1628679649000},"page":"2219-2226","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environment"],"prefix":"10.24963","author":[{"given":"Wilka","family":"Carvalho","sequence":"first","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthony","family":"Liang","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kimin","family":"Lee","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sungryull","family":"Sohn","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honglak","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Michigan"},{"name":"LG AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Lewis","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satinder","family":"Singh","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}","theme":"Artificial Intelligence","location":"Montreal, Canada","acronym":"IJCAI-2021","number":"30","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2021,8,19]]},"end":{"date-parts":[[2021,8,27]]}},"container-title":["Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T11:02:32Z","timestamp":1628679752000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2021\/306"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2021\/306","relation":{},"subject":[],"published":{"date-parts":[[2021,8]]}}}