{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:39:07Z","timestamp":1743039547010,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819916412"},{"type":"electronic","value":"9789819916429"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-981-99-1642-9_41","type":"book-chapter","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T12:14:57Z","timestamp":1681388097000},"page":"480-491","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning from\u00a0Hindsight Demonstrations"],"prefix":"10.1007","author":[{"given":"Mengxuan","family":"Shao","sequence":"first","affiliation":[]},{"given":"Feng","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Shaohui","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Kun","family":"Han","sequence":"additional","affiliation":[]},{"given":"Debin","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,14]]},"reference":[{"key":"41_CR1","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 5055\u20135065 (2017)"},{"key":"41_CR2","unstructured":"Brys, T., Harutyunyan, A., Suay, H.B., Chernova, S., Taylor, M.E., Now\u00e9, A.: Reinforcement learning from demonstration through shaping. In: Twenty-Fourth International Joint Conference on Artificial Intelligence (2015)"},{"issue":"10","key":"41_CR3","doi-asserted-by":"publisher","first-page":"1742","DOI":"10.3390\/electronics9101742","volume":"9","author":"T Dai","year":"2020","unstructured":"Dai, T., Liu, H., Anthony Bharath, A.: Episodic self-imitation learning with hindsight. Electronics 9(10), 1742 (2020)","journal-title":"Electronics"},{"key":"41_CR4","unstructured":"Ding, Y., Florensa, C., Abbeel, P., Phielipp, M.: Goal-conditioned imitation learning. In: Advances in Neural Information Processing Systems, vol. 32, pp. 15324\u201315335 (2019)"},{"key":"41_CR5","unstructured":"Fang, M., Zhou, C., Shi, B., Gong, B., Xu, J., Zhang, T.: DHER: hindsight experience replay for dynamic goals. In: International Conference on Learning Representations (2018)"},{"key":"41_CR6","unstructured":"Fang, M., Zhou, T., Du, Y., Han, L., Zhang, Z.: Curriculum-guided hindsight experience replay. In: Advances in Neural Information Processing Systems, vol. 32, pp. 12623\u201312634 (2019)"},{"key":"41_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. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"41_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":"41_CR9","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. In: Advances in Neural Information Processing Systems, vol. 29, pp. 4565\u20134573 (2016)"},{"key":"41_CR10","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"41_CR11","unstructured":"Liu, H., Trott, A., Socher, R., Xiong, C.: Competitive experience replay. In: International Conference on Learning Representations (2018)"},{"key":"41_CR12","unstructured":"Manela, B., Biess, A.: Curriculum learning with hindsight experience replay for sequential object manipulation tasks. arXiv preprint arXiv:2008.09377 (2020)"},{"key":"41_CR13","unstructured":"Brockman, G., et al.: OpenAI gym (2016)"},{"key":"41_CR14","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"41_CR15","doi-asserted-by":"crossref","unstructured":"Nair, A., McGrew, B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Overcoming exploration in reinforcement learning with demonstrations. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 6292\u20136299. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"41_CR16","doi-asserted-by":"crossref","unstructured":"Peng, X.B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Sim-to-real transfer of robotic control with dynamics randomization. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 3803\u20133810. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"41_CR17","unstructured":"Rauber, P., Ummadisingu, A., Mutz, F., Schmidhuber, J.: Hindsight policy gradients. In: International Conference on Learning Representations (2018)"},{"key":"41_CR18","unstructured":"Rengarajan, D., Vaidya, G., Sarvesh, A., Kalathil, D., Shakkottai, S.: Reinforcement learning with sparse rewards using guidance from offline demonstration. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"41_CR19","unstructured":"Schaul, T., Horgan, D., Gregor, K., Silver, D.: Universal value function approximators. In: International Conference on Machine Learning, pp. 1312\u20131320. PMLR (2015)"},{"key":"41_CR20","unstructured":"van Seijen, H., Fatemi, M., Romoff, J., Laroche, R., Barnes, T., Tsang, J.: Hybrid reward architecture for reinforcement learning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 5398\u20135408 (2017)"},{"issue":"7587","key":"41_CR21","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":"41_CR22","unstructured":"Sutton, R.S., et al.: Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction. In: The 10th International Conference on Autonomous Agents and Multiagent Systems, vol. 2, pp. 761\u2013768 (2011)"},{"key":"41_CR23","unstructured":"Vinyals, O., et al.: Alphastar: mastering the real-time strategy game starcraft II. DeepMind Blog 2 (2019)"},{"key":"41_CR24","unstructured":"Zhao, R., Tresp, V.: Energy-based hindsight experience prioritization. In: Conference on Robot Learning, pp. 113\u2013122. PMLR (2018)"},{"key":"41_CR25","unstructured":"Zhu, Z., Lin, K., Zhou, J.: Transfer learning in deep reinforcement learning: a survey. arXiv preprint arXiv:2009.07888 (2020)"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-1642-9_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T12:32:16Z","timestamp":1681389136000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-1642-9_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819916412","9789819916429"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-1642-9_41","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"14 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","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":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.org\/","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":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","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":"359","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":"44% - 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":"2.65","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":"3","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":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","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)"}}]}}