{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T18:41:08Z","timestamp":1742928068323,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031109850"},{"type":"electronic","value":"9783031109867"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-10986-7_16","type":"book-chapter","created":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T22:30:36Z","timestamp":1658183436000},"page":"200-211","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Incorporating Explanations to\u00a0Balance the\u00a0Exploration and\u00a0Exploitation of\u00a0Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Xinzhi","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yudong","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingjie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,19]]},"reference":[{"key":"16_CR1","unstructured":"Baker, B., et al.: Emergent tool use from multi-agent autocurricula. In: 8th International Conference on Learning Representations. OpenReview.net (2020)"},{"key":"16_CR2","unstructured":"Bellemare, M.G., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying count-based exploration and intrinsic motivation. In: Advances in Neural Information Processing Systems, vol. 29, pp. 1471\u20131479 (2016)"},{"key":"16_CR3","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2021)"},{"key":"16_CR4","unstructured":"Burda, Y., Edwards, H., Pathak, D., Storkey, A., Darrell, T., Efros, A.A.: Large-scale study of curiosity-driven learning. arXiv preprint arXiv:1808.04355 (2018)"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Chakraborty, S., et al.: Interpretability of deep learning models: a survey of results. In: Smartworld, pp. 1\u20136 (2017)","DOI":"10.1109\/UIC-ATC.2017.8397411"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Fong, R.C., Vedaldi, A.: Interpretable explanations of black boxes by meaningful perturbation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3429\u20133437 (2017)","DOI":"10.1109\/ICCV.2017.371"},{"key":"16_CR7","unstructured":"Fortunato, M., et al.: Noisy networks for exploration. arXiv preprint arXiv:1706.10295 (2017)"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Fran\u00e7ois-Lavet, V., Bengio, Y., Precup, D., Pineau, J.: Combined reinforcement learning via abstract representations. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3582\u20133589 (2019)","DOI":"10.1609\/aaai.v33i01.33013582"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Fukui, H., Hirakawa, T., Yamashita, T., Fujiyoshi, H.: Attention branch network: learning of attention mechanism for visual explanation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10705\u201310714 (2019)","DOI":"10.1109\/CVPR.2019.01096"},{"key":"16_CR10","unstructured":"Goyal, A., et al.: InfoBot: transfer and exploration via the information bottleneck. arXiv preprint arXiv:1901.10902 (2019)"},{"key":"16_CR11","unstructured":"Greydanus, S., Koul, A., Dodge, J., Fern, A.: Visualizing and understanding Atari agents. In: International Conference on Machine Learning, pp. 1792\u20131801 (2018)"},{"key":"16_CR12","unstructured":"Houthooft, R., Chen, X., Duan, Y., Schulman, J., De Turck, F., Abbeel, P.: VIME: variational information maximizing exploration. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"16_CR13","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016)"},{"issue":"7540","key":"16_CR14","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\u2013533 (2015)","journal-title":"Nature"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: International Conference on Machine Learning, pp. 2778\u20132787. PMLR (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"16_CR16","unstructured":"Plappert, M., et al.: Parameter space noise for exploration. arXiv preprint arXiv:1706.01905 (2017)"},{"key":"16_CR17","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"16_CR19","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"16_CR20","unstructured":"Tang, H., et al.: Exploration: a study of count-based exploration for deep reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 30, pp. 2753\u20132762 (2017)"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"issue":"7782","key":"16_CR22","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"issue":"4","key":"16_CR23","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1007\/s10796-017-9786-7","volume":"20","author":"X Wang","year":"2018","unstructured":"Wang, X., Sugumaran, V., Zhang, H., Xu, Z.: A capability assessment model for emergency management organizations. Inf. Syst. Front. 20(4), 653\u2013667 (2018). https:\/\/doi.org\/10.1007\/s10796-017-9786-7","journal-title":"Inf. Syst. Front."},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Wang, X., Yuan, S., Zhang, H., Lewis, M., Sycara, K.P.: Verbal explanations for deep reinforcement learning neural networks with attention on extracted features. In: 28th IEEE International Conference on Robot and Human Interactive Communication, pp. 1\u20137. IEEE (2019)","DOI":"10.1109\/RO-MAN46459.2019.8956301"},{"key":"16_CR25","unstructured":"Zintgraf, L.M., et al.: VariBAD: variational Bayes-adaptive deep RL via meta-learning. J. Mach. Learn. Res. 22, 289:1\u2013289:39 (2021)"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-10986-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T22:34:25Z","timestamp":1658183665000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-10986-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031109850","9783031109867"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-10986-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"19 July 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem22.smart-conf.net\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"498","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"169","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"34% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}