{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:38:02Z","timestamp":1742913482205,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819784899"},{"type":"electronic","value":"9789819784905"}],"license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8490-5_31","type":"book-chapter","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T09:10:06Z","timestamp":1730884206000},"page":"435-447","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generatice Adversarial Imitation Learning Algorithm Based on Improved Curiosity Module"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6071-8370","authenticated-orcid":false,"given":"Yongfeng","family":"Fu","sequence":"first","affiliation":[]},{"given":"Quan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xiongzhen","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Huazhang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Lan","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Ke, L., Choudhury, S., Barnes, M., Sun, W., Lee, G., Srinivasa, S.: Imitation learning as f-divergence minimization. In: Algorithmic Foundations of Robotics XIV: Proceedings of the Fourteenth Workshop on the Algorithmic Foundations of Robotics 14. Springer, 2021, pp. 313\u2013329","DOI":"10.1007\/978-3-030-66723-8_19"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Moerland, T.M., Broekens, J., Plaat, A. and Jonker, C.M. et\u00a0al.: Model-based reinforcement learning: A survey. Foundat. Trends\u00ae Mach. Learn.\u00a016(1), 1\u2013118 (2023)","DOI":"10.1561\/2200000086"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Nishio, D.,\u00a0Tsuneda, T.,\u00a0Kuyoshi, D.,\u00a0Yamane, S.: Discriminator soft actor critic without extrinsic rewards. In: 2020 IEEE 9th Global Conference on Consumer Electronics, pp. 117\u2013120. IEEE (2020)","DOI":"10.1109\/GCCE50665.2020.9292009"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, X.,\u00a0Liu, Q.,\u00a0Zhang, L.: Cosine similarity based representation learning for adversarial imitation learning. In: 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 591\u2013596. IEEE (2023)","DOI":"10.1109\/SMC53992.2023.10394257"},{"key":"31_CR5","unstructured":"Orsini, M., Raichuk, A., Hussenot, L., Vincent, D., Dadashi, R., Girgin, S., Geist, M., Bachem, O., Pietquin, O., Andrychowicz, M.: What matters for adversarial imitation learning? Adv. Neural Inf. Process. Syst.\u00a034, 14\u00a0656\u201314\u00a0668 (2021)"},{"key":"31_CR6","first-page":"3016","volume":"34","author":"R Rafailov","year":"2021","unstructured":"Rafailov, R., Yu, T., Rajeswaran, A., Finn, C.: Visual adversarial imitation learning using variational models. Adv. Neural. Inf. Process. Syst. 34, 3016\u20133028 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"31_CR7","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. In: Advances in Neural Information Processing Systems, vol.\u00a029 (2016)"},{"issue":"1","key":"31_CR8","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","volume":"35","author":"A Creswell","year":"2018","unstructured":"Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., Bharath, A.A.: Generative adversarial networks: An overview. IEEE Signal Process. Mag. 35(1), 53\u201365 (2018)","journal-title":"IEEE Signal Process. Mag."},{"issue":"30","key":"31_CR9","first-page":"1","volume":"22","author":"O Kroemer","year":"2021","unstructured":"Kroemer, O., Niekum, S., Konidaris, G.: A review of robot learning for manipulation: Challenges, representations, and algorithms. J. Mach. Learn. Res. 22(30), 1\u201382 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"31_CR10","unstructured":"Kostrikov, I., Agrawal, K.K., Dwibedi, D., Levine, S. and Tompson, J.: Discriminator-actor-critic: Addressing sample inefficiency and reward bias in adversarial imitation learning. In: International Conference on Learning Representations (2018)"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Wu, J., Wu, Q.J., Chen, S., Pourpanah, F., Huang, D.: A-td3: An adaptive asynchronous twin delayed deep deterministic for continuous action spaces. In: IEEE Access, vol.\u00a010, pp. 128\u00a0077\u2013128\u00a0089 (2022)","DOI":"10.1109\/ACCESS.2022.3226446"},{"issue":"2","key":"31_CR12","doi-asserted-by":"publisher","first-page":"221","DOI":"10.3390\/e22020221","volume":"22","author":"F Nielsen","year":"2020","unstructured":"Nielsen, F.: On a generalization of the jensen-shannon divergence and the jensen-shannon centroid. Entropy 22(2), 221 (2020)","journal-title":"Entropy"},{"key":"31_CR13","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1016\/j.procs.2022.11.055","volume":"213","author":"A Andronenko","year":"2022","unstructured":"Andronenko, A., Gryaznov, A., Demin, V.: Implementation of value based curiosity mechanism in reinforcement learning algorithm based on a3c. Proc. Comput. Sci. 213, 190\u2013195 (2022)","journal-title":"Proc. Comput. Sci."},{"issue":"1","key":"31_CR14","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s10994-021-06003-9","volume":"111","author":"V-L Nguyen","year":"2022","unstructured":"Nguyen, V.-L., Shaker, M.H., H\u00fcllermeier, E.: How to measure uncertainty in uncertainty sampling for active learning. Mach. Learn. 111(1), 89\u2013122 (2022)","journal-title":"Mach. Learn."},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Wu, J.,\u00a0Huang, Z.,\u00a0Thoma, J.,\u00a0Acharya, D., Van\u00a0Gool, L.: Wasserstein divergence for gans. In: Proceedings of the European Conference on Computer Vision, 2018, pp. 653\u2013668 (2018)","DOI":"10.1007\/978-3-030-01228-1_40"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Garcia, F., Rachelson, E.: Markov decision processes. In: Markov Decision Processes in Artificial Intelligence, pp. 1\u201338 (2013)","DOI":"10.1002\/9781118557426.ch1"},{"key":"31_CR17","unstructured":"Fei, Y., Yang, Z., Chen, Y., Wang, Z.: Exponential bellman equation and improved regret bounds for risk-sensitive reinforcement learning. Adv. Neural Inf. Process. Syst.\u00a034, 20\u00a0436\u201320\u00a0446 (2021)"},{"issue":"4","key":"31_CR18","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.1109\/TCCN.2019.2952909","volume":"5","author":"C Zhong","year":"2019","unstructured":"Zhong, C., Lu, Z., Gursoy, M.C., Velipasalar, S.: A deep actor-critic reinforcement learning framework for dynamic multichannel access. IEEE Trans. Cognit. Commun. Netw. 5(4), 1125\u20131139 (2019)","journal-title":"IEEE Trans. Cognit. Commun. Netw."},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, M., Wang, Y., Ma, X., Xia, L., Yang, J., Li, Z. and Li, X.: Wasserstein distance guided adversarial imitation learning with reward shape exploration. In: Data Driven Control and Learning Systems Conference, 2020, pp. 1165\u20131170 (2020)","DOI":"10.1109\/DDCLS49620.2020.9275169"},{"issue":"3","key":"31_CR20","doi-asserted-by":"publisher","first-page":"486","DOI":"10.3390\/electronics9030486","volume":"9","author":"C Wu","year":"2020","unstructured":"Wu, C., Ju, B., Wu, Y., Xiong, N.N., Zhang, S.: Wgan-e: A generative adversarial networks for facial feature security. Electronics 9(3), 486 (2020)","journal-title":"Electronics"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Singh, M., Atieh, A., Aly, M.H. and Abd El-Mottaleb, S.A.: 120 gbps sac-ocdma-oam-based fso transmission system: Performance evaluation under different weather conditions. Alexandria Engin. J.\u00a061(12), 10\u00a0407\u201310\u00a0418 (2022)","DOI":"10.1016\/j.aej.2022.03.070"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8490-5_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T09:16:55Z","timestamp":1730884615000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8490-5_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"ISBN":["9789819784899","9789819784905"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8490-5_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,7]]},"assertion":[{"value":"7 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}