{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:43:29Z","timestamp":1740123809020,"version":"3.37.3"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,2,11]],"date-time":"2020-02-11T00:00:00Z","timestamp":1581379200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,2,11]],"date-time":"2020-02-11T00:00:00Z","timestamp":1581379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"NRF of Korea","award":["NRF-2018R1D1A1B07043858","2018R1D1A1B07049923"],"award-info":[{"award-number":["NRF-2018R1D1A1B07043858","2018R1D1A1B07049923"]}]},{"DOI":"10.13039\/501100003708","name":"KISTI","doi-asserted-by":"crossref","award":["K-19-L02-C07-S01"],"award-info":[{"award-number":["K-19-L02-C07-S01"]}],"id":[{"id":"10.13039\/501100003708","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003662","name":"Korea Evaluation Institute of Industrial Technology","doi-asserted-by":"publisher","award":["P0006720"],"award-info":[{"award-number":["P0006720"]}],"id":[{"id":"10.13039\/501100003662","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s11280-019-00763-0","type":"journal-article","created":{"date-parts":[[2020,2,11]],"date-time":"2020-02-11T08:02:36Z","timestamp":1581408156000},"page":"1275-1297","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Accelerated deep reinforcement learning with efficient demonstration utilization techniques"],"prefix":"10.1007","volume":"24","author":[{"given":"Sangho","family":"Yeo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangyoon","family":"Oh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9601-3863","authenticated-orcid":false,"given":"Minsu","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,2,11]]},"reference":[{"key":"763_CR1","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., et al.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"763_CR2","unstructured":"Brockman, G., et al.: Openai gym. arXiv:1606.01540 (2016)"},{"key":"763_CR3","unstructured":"Dhariwal, P., et al.: OpenAI Baselines: high-quality implementations of reinforcement learning algorithms. https:\/\/github.com\/openai\/baselines (2019). Accessed 25 Apr 2019"},{"key":"763_CR4","unstructured":"Espeholt, L., et al.: Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures. arXiv:1802.01561 (2018)"},{"key":"763_CR5","unstructured":"Gao, Y., et al.: Reinforcement learning from imperfect demonstrations. arXiv:1802.05313 (2018)"},{"key":"763_CR6","unstructured":"Garmulewicz, M., Michalewski, H., Mi\u0142o\u015b, P.: Expert-augmented actor-critic for vizdoom and montezumas revenge. arXiv:1809.03447 (2018)"},{"key":"763_CR7","doi-asserted-by":"crossref","unstructured":"Gu, S., Holly, E., Lillicrap, T., Levine, S.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 3389\u20133396 (2017)","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"763_CR8","doi-asserted-by":"crossref","unstructured":"Hester, T., et al.: Deep q-learning from demonstrations. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"763_CR9","unstructured":"Horgan, D., et al.: Distributed prioritized experience replay. arXiv:1803.00933 (2018)"},{"key":"763_CR10","unstructured":"Kurin, V., et al.: The atari grand challenge dataset. arXiv:1705.10998 (2017)"},{"key":"763_CR11","unstructured":"Lakshminarayanan, A.S., Sharma, S., Ravindran, B.: Dynamic frame skip deep q network. arXiv:1605.05365 (2016)"},{"key":"763_CR12","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv :1509.02971 (2015)"},{"key":"763_CR13","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv:1312.5602 (2013)"},{"key":"763_CR14","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"issue":"7540","key":"763_CR15","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature. 518(7540), 529 (2015)","journal-title":"Nature"},{"key":"763_CR16","doi-asserted-by":"crossref","unstructured":"Ng, A.Y., et al.: Feature selection, L1 vs. L2 regularization, and rotational variance. In: Proceedings of the Twenty-First International Conference on Machine Learning, p. 78 (2004)","DOI":"10.1145\/1015330.1015435"},{"key":"763_CR17","unstructured":"OpenAI Authors: OpenAI Five. https:\/\/openai.com\/blog\/openai-five\/ (2018). Accessed 25 Apr 2019"},{"key":"763_CR18","doi-asserted-by":"crossref","unstructured":"Peng, J., et al.: Incremental Multi step Q-learning. Machine Learning Proceedings 1994, pp 226\u2013232 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50035-0"},{"key":"763_CR19","unstructured":"Perez, L., Wang, J.: The effectiveness of data augmentation in image classification using deep learning. arXiv:1712.04621 (2017)"},{"key":"763_CR20","unstructured":"Pohlen, T., et al.: Observe and look further: achieving consistent performance on atari. arXiv:1805.11593 (2018)"},{"key":"763_CR21","unstructured":"Salimans, T., Chen, R.: Learning Montezuma\u2019s revenge from a single demonstration. arXiv:1812.03381 (2018)"},{"issue":"19","key":"763_CR22","doi-asserted-by":"publisher","first-page":"70","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023","volume":"2017","author":"AEL Sallab","year":"2017","unstructured":"Sallab, A.E.L., et al.: Deep reinforcement learning framework for autonomous driving. Electron. Imag. 2017(19), 70\u201376 (2017)","journal-title":"Electron. Imag."},{"key":"763_CR23","unstructured":"Schulman, J., et al.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897 (2015)"},{"key":"763_CR24","doi-asserted-by":"crossref","unstructured":"Sharma, S., Lakshminarayanan, A.S., Ravindran, B.: Learning to repeat: Fine grained action repetition for deep reinforcement learning. arXiv:1702.06054 (2017)","DOI":"10.1609\/aaai.v31i1.10918"},{"issue":"7587","key":"763_CR25","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature. 529(7587), 484 (2016)","journal-title":"Nature"},{"key":"763_CR26","unstructured":"Stadie, B.C., Abbeel, P., Sutskever, I..: Third-person imitation learning. arXiv:1703.01703 (2017)"},{"key":"763_CR27","unstructured":"Stooke, A., Abbeel, P.: Accelerated methods for deep reinforcement learning. arXiv:1803.02811 (2018)"},{"key":"763_CR28","unstructured":"TensorFlow Authors: tensorflow\/tensorflow. An Open Source Machine Learning Framework for Everyone. https:\/\/github.com\/tensorflow\/tensorflow (2019). Accessed 25 Apr 2019"},{"key":"763_CR29","doi-asserted-by":"crossref","unstructured":"Yeo, S., Oh, S., Lee, M.: Accelerating deep reinforcement learning using human demonstration data based on replay buffer management and online frame skipping. In: 2019 IEEE International Conference on Big Data and Smart Computing (BigComp), pp. 1\u20138 (2019)","DOI":"10.1109\/BIGCOMP.2019.8679366"},{"key":"763_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Atari-HEAD: Atari human eye-tracking and demonstration dataset. arXiv:1903.06754 (2019)","DOI":"10.1609\/aaai.v34i04.6161"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-019-00763-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11280-019-00763-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-019-00763-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,15]],"date-time":"2022-10-15T06:45:22Z","timestamp":1665816322000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11280-019-00763-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,11]]},"references-count":30,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["763"],"URL":"https:\/\/doi.org\/10.1007\/s11280-019-00763-0","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"type":"print","value":"1386-145X"},{"type":"electronic","value":"1573-1413"}],"subject":[],"published":{"date-parts":[[2020,2,11]]},"assertion":[{"value":"1 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}