{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T13:13:02Z","timestamp":1744290782630,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819916382"},{"type":"electronic","value":"9789819916399"}],"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\/978-981-99-1639-9_1","type":"book-chapter","created":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T07:02:39Z","timestamp":1681455759000},"page":"3-14","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Knowledge Transfer from\u00a0Situation Evaluation to\u00a0Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1938-2603","authenticated-orcid":false,"given":"Min","family":"Chen","sequence":"first","affiliation":[]},{"given":"Zhiqiang","family":"Pu","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Jianqiang","family":"Yi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,15]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Arora, S., Doshi, P.: A survey of inverse reinforcement learning: challenges, methods and progress. Artif. Intell. 297(C), 103500 (2021)","DOI":"10.1016\/j.artint.2021.103500"},{"key":"1_CR2","unstructured":"Berner, C., et al.: Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019)"},{"key":"1_CR3","unstructured":"Burda, Y., Edwards, H., Pathak, D., Storkey, A., Darrell, T., Efros, A.A.: Large-scale study of curiosity-driven learning. In: International Conference on Learning Representations (2018)"},{"key":"1_CR4","unstructured":"Chenghao, L., Wang, T., Wu, C., Zhao, Q., Yang, J., Zhang, C.: Celebrating diversity in shared multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"1_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"1_CR6","unstructured":"Devlin, S., Kudenko, D.: Theoretical considerations of potential-based reward shaping for multi-agent systems. In: The 10th International Conference on Autonomous Agents and Multiagent Systems. pp. 225\u2013232. ACM (2011)"},{"key":"1_CR7","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":"1_CR8","unstructured":"Finn, C., Levine, S., Abbeel, P.: Guided cost learning: deep inverse optimal control via policy optimization. In: International Conference on Machine Learning, pp. 49\u201358. PMLR (2016)"},{"key":"1_CR9","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":"1_CR10","first-page":"15931","volume":"33","author":"Y Hu","year":"2020","unstructured":"Hu, Y., et al.: Learning to utilize shaping rewards: a new approach of reward shaping. Adv. Neural Inf. Process. Syst. 33, 15931\u201315941 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"6443","key":"1_CR11","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1126\/science.aau6249","volume":"364","author":"M Jaderberg","year":"2019","unstructured":"Jaderberg, M., et al.: Human-level performance in 3d multiplayer games with population-based reinforcement learning. Science 364(6443), 859\u2013865 (2019)","journal-title":"Science"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Kurach, K., et al.: Google research football: a novel reinforcement learning environment. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 4501\u20134510 (2020)","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Lample, G., Chaplot, D.S.: Playing fps games with deep reinforcement learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"1_CR14","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"1_CR15","unstructured":"Ma, X., Yang, Y., Li, C., Lu, Y., Zhao, Q., Jun, Y.: Modeling the interaction between agents in cooperative multi-agent reinforcement learning. arXiv preprint arXiv:2102.06042 (2021)"},{"key":"1_CR16","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"1_CR17","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":"1_CR18","series-title":"BRIEFSINSY","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8","volume-title":"A concise introduction to decentralized POMDPs","author":"FA Oliehoek","year":"2016","unstructured":"Oliehoek, F.A., Amato, C.: A concise introduction to decentralized POMDPs. BRIEFSINSY, Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-28929-8"},{"key":"1_CR19","unstructured":"Peng, X.B., Kanazawa, A., Toyer, S., Abbeel, P., Levine, S.: Variational discriminator bottleneck: improving imitation learning, inverse RL, and GANs by constraining information flow (2020)"},{"key":"1_CR20","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)"},{"key":"1_CR21","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4295\u20134304. PMLR (2018)"},{"key":"1_CR22","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"1_CR23","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"1_CR24","unstructured":"Son, K., Kim, D., Kang, W.J., Hostallero, D.E., Yi, Y.: Qtran: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5887\u20135896. PMLR (2019)"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Song, S., Weng, J., Su, H., Yan, D., Zou, H., Zhu, J.: Playing fps games with environment-aware hierarchical reinforcement learning. In: IJCAI, pp. 3475\u20133482 (2019)","DOI":"10.24963\/ijcai.2019\/482"},{"key":"1_CR26","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"key":"1_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"7782","key":"1_CR28","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., Babuschkin, I., Czarnecki, W.M., Mathieu, M., Dudzik, A., Chung, J., Choi, D.H., Powell, R., Ewalds, T., Georgiev, P., et al.: Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"key":"1_CR29","unstructured":"Wang, J., Ren, Z., Liu, T., Yu, Y., Zhang, C.: Qplex: Duplex dueling multi-agent q-learning. arXiv preprint arXiv:2008.01062 (2020)"},{"key":"1_CR30","unstructured":"Wang, T., Dong, H., Lesser, V., Zhang, C.: Roma: multi-agent reinforcement learning with emergent roles. In: International Conference on Machine Learning, pp. 9876\u20139886. PMLR (2020)"},{"key":"1_CR31","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":"1_CR32","unstructured":"Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"1_CR33","unstructured":"Yu, C., Velu, A., Vinitsky, E., Wang, Y., Bayen, A., Wu, Y.: The surprising effectiveness of PPO in cooperative, multi-agent games. arXiv preprint arXiv:2103.01955 (2021)"},{"key":"1_CR34","unstructured":"Zheng, Z., et al.: What can learned intrinsic rewards capture? In: International Conference on Machine Learning, pp. 11436\u201311446. PMLR (2020)"},{"key":"1_CR35","unstructured":"Zheng, Z., Oh, J., Singh, S.: On learning intrinsic rewards for policy gradient methods. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"}],"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\/978-981-99-1639-9_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T07:21:20Z","timestamp":1681456880000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-1639-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819916382","9789819916399"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-1639-9_1","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":"15 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)"}}]}}