{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:13:25Z","timestamp":1742991205974,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642154195"},{"type":"electronic","value":"9783642154201"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-15420-1_10","type":"book-chapter","created":{"date-parts":[[2010,8,26]],"date-time":"2010-08-26T23:22:45Z","timestamp":1282864965000},"page":"115-125","source":"Crossref","is-referenced-by-count":2,"title":["Time-Based Reward Shaping in Real-Time Strategy Games"],"prefix":"10.1007","author":[{"given":"Martin","family":"Midtgaard","sequence":"first","affiliation":[]},{"given":"Lars","family":"Vinther","sequence":"additional","affiliation":[]},{"given":"Jeppe R.","family":"Christiansen","sequence":"additional","affiliation":[]},{"given":"Allan M.","family":"Christensen","sequence":"additional","affiliation":[]},{"given":"Yifeng","family":"Zeng","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"10_CR1","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R. Sutton","year":"1999","unstructured":"Sutton, R., Precup, D., Singh, S.: Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning. Artificial Intelligence\u00a0112, 181\u2013211 (1999)","journal-title":"Artificial Intelligence"},{"key":"10_CR2","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"10_CR3","unstructured":"Ghory, I.: Reinforcement learning in board games. Technical Report, Department of Computer Science, University of Bristol (2004)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the Eleventh International Conference on Machine Learning, pp. 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Mataric, M.J.: Reward Functions for Accelerated Learning. In: Proceedings of the Eleventh International Conference on Machine Learning, pp. 181\u2013189 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50030-1"},{"key":"10_CR6","unstructured":"Sharma, M., Holmes, M., Santamaria, J., Irani, A., Isbell, C., Ram, A.: Transfer Learning in Real-Time Strategy Games Using Hybrid CBR\/RL. In: Proceedings of the 20th International Joint Conference on Artifical Intelligence, pp. 1041\u20131046 (2007)"},{"key":"10_CR7","unstructured":"Marthi, B., Russell, S., Latham, D., Guestrin, C.: Concurrent Hierarchical Reinforcement Learning. In: Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, pp. 779\u2013785 (2005)"},{"key":"10_CR8","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: Theory and application to reward shaping. In: Proceedings of the Sixteenth International Conference on Machine Learning, pp. 278\u2013287 (1999)"},{"key":"10_CR9","unstructured":"Laud, A.D.: Theory and application of reward shaping in reinforcement learning. University of Illinois at Urbana-Champaign (2004)"},{"issue":"9","key":"10_CR10","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1080\/08839510903246526","volume":"23","author":"K.T. Andersen","year":"2009","unstructured":"Andersen, K.T., Zeng, Y.F., Tran, D., Christensen, D.D.: Experiments with Online Reinforcement Learning in Real-Time Strategy Games. Applied Artificial Intelligence: An International Journal\u00a023(9), 855\u2013871 (2009)","journal-title":"Applied Artificial Intelligence: An International Journal"},{"key":"10_CR11","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"2","key":"10_CR12","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1162\/neco.1994.6.2.215","volume":"6","author":"G.. Tesauro","year":"1994","unstructured":"Tesauro, G.: Td-gammon, a self-teaching backgammon program, achieves master-level play. Neural Comput.\u00a06(2), 215\u2013219 (1994)","journal-title":"Neural Comput."},{"key":"10_CR13","first-page":"591","volume":"2","author":"Manslow","year":"2004","unstructured":"Manslow: Using reinforcement learning to solve ai control problems. AI Game Programming Wisdom\u00a02, 591\u2013601 (2004)","journal-title":"AI Game Programming Wisdom"}],"container-title":["Lecture Notes in Computer Science","Agents and Data Mining Interaction"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-15420-1_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T23:46:31Z","timestamp":1552952791000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-15420-1_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642154195","9783642154201"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-15420-1_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}