{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:08:26Z","timestamp":1766066906966,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,4,9]],"date-time":"2018-04-09T00:00:00Z","timestamp":1523232000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,4,9]]},"DOI":"10.1145\/3167132.3167165","type":"proceedings-article","created":{"date-parts":[[2018,7,3]],"date-time":"2018-07-03T13:54:10Z","timestamp":1530626050000},"page":"331-338","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Deep reinforcement learning boosted by external knowledge"],"prefix":"10.1145","author":[{"given":"Nicolas","family":"Bougie","sequence":"first","affiliation":[{"name":"National Institute of Informatics, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryutaro","family":"Ichise","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,4,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025696116075"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"volume-title":"Hausknecht and Peter Stone","year":"2015","author":"Matthew","key":"e_1_3_2_1_3_1"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3061053.3061259"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"volume-title":"Kingma and Jimmy Ba","year":"2014","author":"Diederik","key":"e_1_3_2_1_7_1"},{"volume-title":"Tsitsiklis","year":"1999","author":"Konda Vijay R.","key":"e_1_3_2_1_8_1"},{"volume-title":"Gershman","year":"2016","author":"Lake Brenden M.","key":"e_1_3_2_1_9_1"},{"volume-title":"Proceedings of AAAI. 2140--2146","year":"2017","author":"Lample Guillaume","key":"e_1_3_2_1_10_1"},{"volume-title":"The knowledge level in cognitive architectures: Current limitations and possible developments. Cognitive Systems Research","year":"2017","author":"Lieto Antonio","key":"e_1_3_2_1_11_1"},{"volume-title":"Continuous control with deep reinforcement learning. ArXiv e-prints (Sept","year":"2015","author":"Lillicrap Timothy P.","key":"e_1_3_2_1_12_1"},{"volume-title":"Proceedings of International Conference on Machine Learning. 1928--1937","year":"2016","author":"Mnih Volodymyr","key":"e_1_3_2_1_13_1"},{"key":"e_1_3_2_1_14_1","unstructured":"V. Mnih K. Kavukcuoglu D. Silver A. Graves I. Antonoglou D. Wierstra and M. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. ArXiv e-prints (Dec. 2013). arXiv:cs.LG\/1312.5602  V. Mnih K. Kavukcuoglu D. Silver A. Graves I. Antonoglou D. Wierstra and M. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. ArXiv e-prints (Dec. 2013). arXiv:cs.LG\/1312.5602"},{"key":"e_1_3_2_1_15_1","unstructured":"Oltramari and Lebiere. 2012. Using Ontologies in a Cognitive-Grounded System: Automatic Action Recognition in Video-Surveillance. (2012).  Oltramari and Lebiere. 2012. Using Ontologies in a Cognitive-Grounded System: Automatic Action Recognition in Video-Surveillance. (2012)."},{"volume-title":"Ross B. Girshick, and Ali Farhadi.","year":"2015","author":"Redmon Joseph","key":"e_1_3_2_1_16_1"},{"volume-title":"Faster, Stronger. CoRR abs\/1612.08242","year":"2016","author":"Redmon Joseph","key":"e_1_3_2_1_17_1"},{"key":"e_1_3_2_1_18_1","unstructured":"G. A. Rummery and M. Niranjan. 1994. On-Line Q-Learning Using Connectionist Systems. Technical Report. University of Cambridge.  G. A. Rummery and M. Niranjan. 1994. On-Line Q-Learning Using Connectionist Systems. Technical Report. University of Cambridge."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"volume-title":"Proceedings of AAAI Conference on Artificial Intelligence. 1553--1561","year":"2017","author":"Tessler Chen","key":"e_1_3_2_1_20_1"},{"volume-title":"Divide the gradient by a running average of its recent magnitude","year":"2012","author":"Tieleman Tijmen","key":"e_1_3_2_1_21_1"},{"volume-title":"Deep Reinforcement Learning with Double Q-learning. CoRR abs\/1509.06461","year":"2015","author":"van Hasselt Hado","key":"e_1_3_2_1_22_1"},{"volume-title":"Proceedings of the 33rd International Conference on Machine Learning, ICML 2016","year":"2016","author":"Wang Ziyu","key":"e_1_3_2_1_23_1"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"}],"event":{"name":"SAC 2018: Symposium on Applied Computing","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"],"location":"Pau France","acronym":"SAC 2018"},"container-title":["Proceedings of the 33rd Annual ACM Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3167132.3167165","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3167132.3167165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:13:28Z","timestamp":1750212808000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3167132.3167165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4,9]]},"references-count":24,"alternative-id":["10.1145\/3167132.3167165","10.1145\/3167132"],"URL":"https:\/\/doi.org\/10.1145\/3167132.3167165","relation":{},"subject":[],"published":{"date-parts":[[2018,4,9]]},"assertion":[{"value":"2018-04-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}