{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T09:15:30Z","timestamp":1743153330169,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030616151"},{"type":"electronic","value":"9783030616168"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-61616-8_27","type":"book-chapter","created":{"date-parts":[[2020,10,16]],"date-time":"2020-10-16T23:07:42Z","timestamp":1602889662000},"page":"335-345","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Guided Reinforcement Learning via Sequence Learning"],"prefix":"10.1007","author":[{"given":"Rajkumar","family":"Ramamurthy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafet","family":"Sifa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max","family":"L\u00fcbbering","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Bauckhage","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,10,14]]},"reference":[{"key":"27_CR1","unstructured":"Bellemare, M.G., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying Count-Based Exploration and Intrinsic Motivation. arXiv preprint arXiv:1606.01868 (2016)"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"27_CR3","unstructured":"Christiano, P.F., Leike, J., Brown, T., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences. In: Advances in Neural Information Processing Systems, pp. 4299\u20134307 (2017)"},{"key":"27_CR4","unstructured":"Conti, E., Madhavan, V., Such, F.P., Lehman, J., Stanley, K.O., Clune, J.: Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents. arXiv preprint arXiv:1712.06560 (2017)"},{"key":"27_CR5","unstructured":"Du, Y., Czarnecki, W.M., Jayakumar, S.M., Pascanu, R., Lakshminarayanan, B.: Adapting Auxiliary Losses using Gradient Similarity. arXiv preprint arXiv:1812.02224 (2018)"},{"key":"27_CR6","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: Proceedings of International Conference on Robotics and Automation (2017)","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"27_CR7","unstructured":"Jaderberg, M., et al.: Reinforcement Learning with Unsupervised Auxiliary Tasks. arXiv preprint arXiv:1611.05397 (2016)"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Kartal, B., Hernandez-Leal, P., Taylor, M.E.: Terminal prediction as an auxiliary task for deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (2019)","DOI":"10.1609\/aiide.v15i1.5222"},{"issue":"2","key":"27_CR9","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1162\/EVCO_a_00025","volume":"19","author":"J Lehman","year":"2011","unstructured":"Lehman, J., Stanley, K.O.: Abandoning objectives: evolution through the search for novelty alone. Evol. Comput. 19(2), 189\u2013223 (2011)","journal-title":"Evol. Comput."},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Lehman, J., Stanley, K.O.: Evolving a diversity of virtual creatures through novelty search and local competition. In: Proceedings of International Conference on Genetic and Evolutionary Computation (2011)","DOI":"10.1145\/2001576.2001606"},{"key":"27_CR11","unstructured":"Makhzani, A., Frey, B.: K-sparse autoencoders. arXiv preprint arXiv:1312.5663 (2013)"},{"key":"27_CR12","unstructured":"Mirowski, P., et al.: Learning to Navigate in Complex Environments. arXiv preprint arXiv:1611.03673 (2016)"},{"key":"27_CR13","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, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"27_CR14","unstructured":"Ostrovski, G., Bellemare, M.G., van den Oord, A., Munos, R.: Count-Based Exploration with Neural Density Models (2017)"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: Proceedings of International Conference on Machine Learning (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"27_CR16","unstructured":"Pathak, D., Gandhi, D., Gupta, A.: Self-Supervised Exploration via Disagreement. arXiv preprint arXiv:1906.04161 (2019)"},{"key":"27_CR17","unstructured":"Ramamurthy, R.: Pytorch-Optimize - A Black Box Optimization Framework. https:\/\/github.com\/rajcscw\/pytorch-optimize (2020)"},{"key":"27_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1007\/978-3-030-30484-3_48","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Deep Learning","author":"R Ramamurthy","year":"2019","unstructured":"Ramamurthy, R., Bauckhage, C., Sifa, R., Sch\u00fccker, J., Wrobel, S.: Leveraging domain knowledge for reinforcement learning using MMC architectures. In: Tetko, I.V., K\u016frkov\u00e1, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11728, pp. 595\u2013607. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30484-3_48"},{"key":"27_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01424-7_1","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2018","author":"R Ramamurthy","year":"2018","unstructured":"Ramamurthy, R., Bauckhage, C., Sifa, R., Wrobel, S.: Policy learning using SPSA. In: K\u016frkov\u00e1, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11141, pp. 3\u201312. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01424-7_1"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Ramamurthy, R., Sifa, R., L\u00fcbbering, M., Bauckhage, C.: Novelty-guided reinforcement learning via encoded behaviors. In: Proceedings of International Joint Conference on Neural Networks (2020)","DOI":"10.1109\/IJCNN48605.2020.9206982"},{"key":"27_CR21","unstructured":"Rechenberg, I.: Evolutionsstrategie: Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. Ph.D. thesis, Technical University of Berlin, Department of Process Engineering (1971)"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Rechenberg, I.: Evolutionsstrategien. In: Simulationsmethoden in der Medizin und Biologie (1978)","DOI":"10.1007\/978-3-642-81283-5_8"},{"key":"27_CR23","unstructured":"Salimans, T., Ho, J., Chen, X., Sutskever, I.: Evolution Strategies as a Scalable Alternative to Reinforcement Learning. arXiv:1703.03864 (2017)"},{"key":"27_CR24","unstructured":"Schmidhuber, J.: Formal theory of creativity, fun, and intrinsic motivation (1990\u20132010). IEEE Trans. Auton. Mental Dev. 2, 230\u2013247 (2010)"},{"key":"27_CR25","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: Proceedings of International Conference on Machine Learning (2015)"},{"key":"27_CR26","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: Proceedings of International Conference on Machine Learning (2014)"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","DOI":"10.1038\/nature24270"},{"key":"27_CR28","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: Proceedings of International Conference on Machine Learning (2015)"},{"key":"27_CR29","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings in Neural Information Processing Systems (2014)"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Target-driven visual navigation in indoor scenes using deep reinforcement learning. In: Proceedings of International Conference on Robotics and Automation (2017)","DOI":"10.1109\/ICRA.2017.7989381"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-61616-8_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T18:28:55Z","timestamp":1669228135000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-61616-8_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030616151","9783030616168"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-61616-8_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"14 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bratislava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovakia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2020\/","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":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"249","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":"139","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":"56% - 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":"2.5","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)"}},{"value":"*The conference was postponed to 2021 due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}