{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T21:02:23Z","timestamp":1784408543306,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819233809","type":"print"},{"value":"9789819233816","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3381-6_38","type":"book-chapter","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:15:20Z","timestamp":1784405720000},"page":"467-478","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RAISE: Reward-Aware Intrinsic Learning for Sparse Extrinsic Reward Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Wenhao","family":"Yue","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junteng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"38_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2022.03.003","volume":"85","author":"P Ladosz","year":"2022","unstructured":"Ladosz, P., Weng, L., Kim, M., Oh, H.: Exploration in deep reinforcement learning: a survey. Inf. Fusion. 85, 1\u201322 (2022)","journal-title":"Inf. Fusion"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Henaff, M., Raileanu, R., Jiang, M., Rockt\u00e4schel, T.: Exploration via elliptical episodic bonuses. In: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), pp. 37631\u201337646 (2022)","DOI":"10.52202\/068431-2728"},{"key":"38_CR3","unstructured":"Zheng, Z., Oh, J., Singh, S.: On learning intrinsic rewards for policy gradient methods. In: Advances in Neural Information Processing Systems 31 (NeurIPS 2018) (2018)"},{"key":"38_CR4","unstructured":"Henaff, M., Jiang, M., Raileanu, R.: A study of global and episodic bonuses for exploration in contextual MDPs. In: International Conference on Machine Learning, pp. 12972\u201312999. PMLR (2023)"},{"key":"38_CR5","unstructured":"Bellemare, M., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying count-based exploration and intrinsic motivation. In: Advances in Neural Information Processing Systems 29 (NIPS 2016) (2016)"},{"key":"38_CR6","unstructured":"Pathak, D., Gandhi, D., Gupta, A.: Self-supervised exploration via disagreement. In: International Conference on Machine Learning, pp. 5062\u20135071. PMLR (2019)"},{"issue":"7847","key":"38_CR7","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1038\/s41586-020-03157-9","volume":"590","author":"A Ecoffet","year":"2021","unstructured":"Ecoffet, A., Huizinga, J., Lehman, J., Stanley, K.O., Clune, J.: First return, then explore. Nature. 590(7847), 580\u2013586 (2021)","journal-title":"Nature"},{"issue":"8","key":"38_CR8","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1016\/j.jcss.2007.08.009","volume":"74","author":"AL Strehl","year":"2008","unstructured":"Strehl, A.L., Littman, M.L.: An analysis of model-based interval estimation for Markov decision processes. J. Comput. Syst. Sci. 74(8), 1309\u20131331 (2008)","journal-title":"J. Comput. Syst. Sci."},{"key":"38_CR9","unstructured":"Burda, Y., Edwards, H., Storkey, A., Klimov, O.: Exploration by random network distillation. arXiv preprint arXiv:1810.12894 (2018)"},{"key":"38_CR10","unstructured":"Badia, A.P., et al.: Never give up: Learning directed exploration strategies. arXiv preprint arXiv:2002.06038 (2020)"},{"key":"38_CR11","unstructured":"Raileanu, R., Rockt\u00e4schel, T.: Ride: Rewarding impact-driven exploration for procedurally-generated environments. arXiv preprint arXiv:2002.12292 (2020)"},{"key":"38_CR12","unstructured":"Wang, K., Zhou, K., Kang, B., Feng, J., Yan, S.: Revisiting intrinsic reward for exploration in procedurally generated environments. In: The 11th International Conference on Learning Representations (2023)"},{"key":"38_CR13","unstructured":"Stadie, B., Zhang, L., Ba, J.: Learning intrinsic rewards as a bi-level optimization problem. In: Conference on Uncertainty in Artificial Intelligence, pp. 111\u2013120. PMLR (2020)"},{"key":"38_CR14","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"38_CR15","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"38_CR16","doi-asserted-by":"crossref","unstructured":"Kempka, M., Wydmuch, M., Runc, G., Toczek, J., Ja\u015bkowski, W.: ViZDoom: A doom-based AI research platform for visual reinforcement learning. In: 2016 IEEE Conference on Computational Intelligence and Games (CIG), pp. 1\u20138. IEEE (2016)","DOI":"10.1109\/CIG.2016.7860433"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Chevalier-Boisvert, M., et al.: Minigrid & miniworld: Modular & customizable reinforcement learning environments for goal-oriented tasks. In: Advances in Neural Information Processing Systems 36 (NeurIPS 2023), pp. 73383\u201373394 (2023)","DOI":"10.52202\/075280-3209"},{"key":"38_CR18","doi-asserted-by":"crossref","unstructured":"Mguni, D., et al.: Learning to shape rewards using a game of two partners. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 11604\u201311612 (2023)","DOI":"10.1609\/aaai.v37i10.26371"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Devidze, R., Kamalaruban, P., Singla, A.: Exploration-guided reward shaping for reinforcement learning under sparse rewards. In: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), pp. 5829\u20135842 (2022)","DOI":"10.52202\/068431-0422"},{"key":"38_CR20","doi-asserted-by":"crossref","unstructured":"Wan, S., Tang, Y., Tian, Y., Kaneko, T.: DEIR: Efficient and robust exploration through discriminative-model-based episodic intrinsic rewards. In: Proceedings of the 32nd International Joint Conference on Artificial Intelligence, pp. 4289\u20134298 (2023)","DOI":"10.24963\/ijcai.2023\/477"},{"key":"38_CR21","unstructured":"Ma, H., Sima, K., Vo, T.V., Fu, D., Leong, T.Y.: Reward shaping for reinforcement learning with an assistant reward agent. In: 41st international Conference on Machine Learning (2024)"},{"key":"38_CR22","unstructured":"Tang, H., et al.: #Exploration: a study of count-based exploration for deep reinforcement learning. In: Advances in Neural Information Processing Systems 30 (NIPS 2017) (2017)"},{"key":"38_CR23","doi-asserted-by":"crossref","unstructured":"Memarian, F., Goo, W., Lioutikov, R., Niekum, S., Topcu, U.: Self-supervised online reward shaping in sparse-reward environments. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2369\u20132375. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636020"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3381-6_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:15:22Z","timestamp":1784405722000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3381-6_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"ISBN":["9789819233809","9789819233816"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3381-6_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"19 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}