{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T03:22:59Z","timestamp":1742959379771,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"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_42","type":"book-chapter","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T12:14:57Z","timestamp":1681388097000},"page":"492-503","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hindsight Balanced Reward Shaping"],"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":"42_CR1","unstructured":"Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Man\u00e9, D.: Concrete problems in ai safety. arXiv preprint arXiv:1606.06565 (2016)"},{"key":"42_CR2","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":"42_CR3","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1016\/j.neucom.2019.06.022","volume":"359","author":"C Bai","year":"2019","unstructured":"Bai, C., Liu, P., Zhao, W., Tang, X.: Guided goal generation for hindsight multi-goal reinforcement learning. Neurocomputing 359, 353\u2013367 (2019)","journal-title":"Neurocomputing"},{"key":"42_CR4","unstructured":"Clark, J., Amodei, D.: Faulty reward functions in the wild. Internet (2016). https:\/\/blog.openai.com\/faulty-reward-functions"},{"key":"42_CR5","unstructured":"Devlin, S.M., Kudenko, D.: Dynamic potential-based reward shaping. In: Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems, pp. 433\u2013440. IFAAMAS (2012)"},{"key":"42_CR6","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":"42_CR7","first-page":"12623","volume":"32","author":"M Fang","year":"2019","unstructured":"Fang, M., Zhou, T., Du, Y., Han, L., Zhang, Z.: Curriculum-guided hindsight experience replay. Adv. Neural Inf. Process. Syst. 32, 12623\u201312634 (2019)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"42_CR8","doi-asserted-by":"crossref","unstructured":"Fu, Z.Y., Zhan, D.C., Li, X.C., Lu, Y.X.: Automatic successive reinforcement learning with multiple auxiliary rewards (2019)","DOI":"10.24963\/ijcai.2019\/324"},{"key":"42_CR9","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":"42_CR10","doi-asserted-by":"crossref","unstructured":"Harutyunyan, A., Devlin, S., Vrancx, P., Now\u00e9, A.: Expressing arbitrary reward functions as potential-based advice. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 29 (2015)","DOI":"10.1609\/aaai.v29i1.9628"},{"key":"42_CR11","unstructured":"Hu, Y., et al.: Learning to utilize shaping rewards: a new approach of reward shaping. Adv. Neural Inf. Process. Syst. 33 (2020)"},{"key":"42_CR12","unstructured":"Jiang, K., Qin, X.: Reinforcement learning with goal-distance gradient. arXiv preprint arXiv:2001.00127 (2020)"},{"key":"42_CR13","unstructured":"Manela, B., Biess, A.: Curriculum learning with hindsight experience replay for sequential object manipulation tasks. arXiv preprint arXiv:2008.09377 (2020)"},{"key":"42_CR14","first-page":"9191","volume":"31","author":"AV Nair","year":"2018","unstructured":"Nair, A.V., Pong, V., Dalal, M., Bahl, S., Lin, S., Levine, S.: Visual reinforcement learning with imagined goals. Adv. Neural Inf. Process. Syst. 31, 9191\u20139200 (2018)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"42_CR15","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. In: ICML, vol. 99, pp. 278\u2013287 (1999)"},{"key":"42_CR16","unstructured":"Randl\u00f8v, J., Alstr\u00f8m, P.: Learning to drive a bicycle using reinforcement learning and shaping. In: ICML, vol. 98, pp. 463\u2013471. Citeseer (1998)"},{"key":"42_CR17","unstructured":"Rauber, P., Ummadisingu, A., Mutz, F., Schmidhuber, J.: Hindsight policy gradients. In: International Conference on Learning Representations (2018)"},{"key":"42_CR18","unstructured":"Russell, S.J., Norvig, P.: Artificial intelligence: a modern approach (2010)"},{"key":"42_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":"42_CR20","doi-asserted-by":"crossref","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484 (2016)","DOI":"10.1038\/nature16961"},{"key":"42_CR21","doi-asserted-by":"crossref","unstructured":"Sun, F.Y., Chang, Y.Y., Wu, Y.H., Lin, S.D.: Designing non-greedy reinforcement learning agents with diminishing reward shaping. In: Proceedings of the 2018 AAAI\/ACM Conference on AI, Ethics, and Society, pp. 297\u2013302 (2018)","DOI":"10.1145\/3278721.3278759"},{"key":"42_CR22","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":"42_CR23","unstructured":"Wiewiora, E., Cottrell, G.W., Elkan, C.: Principled methods for advising reinforcement learning agents. In: Proceedings of the 20th International Conference on Machine Learning (ICML-2003), pp. 792\u2013799 (2003)"},{"key":"42_CR24","unstructured":"Zhao, R., Tresp, V.: Energy-based hindsight experience prioritization. In: Conference on Robot Learning, pp. 113\u2013122. PMLR (2018)"},{"key":"42_CR25","unstructured":"Zheng, Z., et al.: What can learned intrinsic rewards capture? In: International Conference on Machine Learning, pp. 11436\u201311446. PMLR (2020)"},{"key":"42_CR26","unstructured":"Zou, H., Ren, T., Yan, D., Su, H., Zhu, J.: Reward shaping via meta-learning. arXiv preprint arXiv:1901.09330 (2019)"}],"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_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T12:32:50Z","timestamp":1681389170000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-1642-9_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819916412","9789819916429"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-1642-9_42","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)"}}]}}