{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:35:25Z","timestamp":1772724925244,"version":"3.50.1"},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T00:00:00Z","timestamp":1662422400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T00:00:00Z","timestamp":1662422400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,9,6]]},"DOI":"10.23919\/sice56594.2022.9905799","type":"proceedings-article","created":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T19:43:18Z","timestamp":1665085398000},"page":"122-127","source":"Crossref","is-referenced-by-count":4,"title":["Multi-Objective Deep Inverse Reinforcement Learning through Direct Weights and Rewards Estimation"],"prefix":"10.23919","author":[{"given":"Daiko","family":"Kishikawa","sequence":"first","affiliation":[{"name":"Chiba University,Department of Urban Environmental Systems,Chiba,Japan"}]},{"given":"Sachiyo","family":"Arai","sequence":"additional","affiliation":[{"name":"Chiba University,Department of Urban Environmental Systems,Chiba,Japan"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"arXiv preprint arXiv 1812 09111"},{"key":"ref11","article-title":"Adam: a method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref12","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref13","article-title":"MountainCarContinuous-v0","year":"0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/AGENTS.2018.8460075"},{"key":"ref3","first-page":"4","article-title":"Reward matrix decomposition for multi-objective inverse reinforcement learning","author":"kishikawa","year":"2022","journal-title":"The 36th Annual Conference of the Japanese Society for Artificial Intelligence 2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1963.1105511"},{"key":"ref5","author":"mitchell","year":"2019","journal-title":"Large-Scale Systems Modeling and Control"},{"key":"ref8","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","author":"brown","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-017-9702-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IIAI-AAI53430.2021.00078"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279964"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"}],"event":{"name":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","location":"Kumamoto, Japan","start":{"date-parts":[[2022,9,6]]},"end":{"date-parts":[[2022,9,9]]}},"container-title":["2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9905734\/9905735\/09905799.pdf?arnumber=9905799","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T21:33:54Z","timestamp":1669066434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9905799\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,6]]},"references-count":13,"URL":"https:\/\/doi.org\/10.23919\/sice56594.2022.9905799","relation":{},"subject":[],"published":{"date-parts":[[2022,9,6]]}}}