{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T07:41:57Z","timestamp":1723016517183},"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":[[2022,7]]},"abstract":"<jats:p>In robotic tasks, we encounter the unique strengths of (1) reinforcement learning (RL) that can handle high-dimensional observations as well as unknown, complex dynamics and (2) planning that can handle sparse and delayed rewards given a dynamics model. Combining these strengths of RL and planning, we propose the Value Refinement Network (VRN), in this work. Our VRN is an RL-trained neural network architecture that learns to locally refine an initial (value-based) plan in a simplified (2D) problem abstraction based on detailed local sensory observations. We evaluate the VRN on simulated robotic (navigation) tasks and demonstrate that it can successfully refine sub-optimal plans to match the performance of more costly planning in the non-simplified problem. Furthermore, in a dynamic environment, the VRN still enables high task completion without global re-planning.<\/jats:p>","DOI":"10.24963\/ijcai.2022\/494","type":"proceedings-article","created":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T22:55:56Z","timestamp":1657925756000},"page":"3558-3565","source":"Crossref","is-referenced-by-count":1,"title":["Value Refinement Network (VRN)"],"prefix":"10.24963","author":[{"given":"Jan","family":"W\u00f6hlke","sequence":"first","affiliation":[{"name":"Bosch Center for Artificial Intelligence"},{"name":"UvA-Bosch Delta Lab, University of Amsterdam"}]},{"given":"Felix","family":"Schmitt","sequence":"additional","affiliation":[{"name":"Bosch Center for Artificial Intelligence"}]},{"given":"Herke","family":"van Hoof","sequence":"additional","affiliation":[{"name":"AMLab, University of Amsterdam"}]}],"member":"10584","event":{"number":"31","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2022","name":"Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}","start":{"date-parts":[[2022,7,23]]},"theme":"Artificial Intelligence","location":"Vienna, Austria","end":{"date-parts":[[2022,7,29]]}},"container-title":["Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T07:10:01Z","timestamp":1658128201000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2022\/494"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2022\/494","relation":{},"subject":[],"published":{"date-parts":[[2022,7]]}}}