{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T14:51:24Z","timestamp":1725807084340},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319119724"},{"type":"electronic","value":"9783319119731"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-11973-1_33","type":"book-chapter","created":{"date-parts":[[2014,10,17]],"date-time":"2014-10-17T01:09:50Z","timestamp":1413508190000},"page":"320-329","source":"Crossref","is-referenced-by-count":2,"title":["Integrating Reinforcement Learning and Declarative Programming to Learn Causal Laws in Dynamic Domains"],"prefix":"10.1007","author":[{"given":"Mohan","family":"Sridharan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarah","family":"Rainge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"33_CR1","unstructured":"Aerolla, M.: Incorporating Human and Environmental Feedback for Robust Performance in Agent Domains. Master\u2019s thesis, Department of Computer Science, Texas Tech University (May 2011)"},{"key":"33_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/978-3-642-40564-8_14","volume-title":"Logic Programming and Nonmonotonic Reasoning","author":"E. Balai","year":"2013","unstructured":"Balai, E., Gelfond, M., Zhang, Y.: Towards Answer Set Programming with Sorts. In: Cabalar, P., Son, T.C. (eds.) LPNMR 2013. LNCS, vol.\u00a08148, pp. 135\u2013147. Springer, Heidelberg (2013)"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Baral, C.: Knowledge Representation, Reasoning and Declarative Problem Solving. Cambridge University Press (2003)","DOI":"10.1017\/CBO9780511543357"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Blumberg, B., Downie, M., Ivanov, Y., Berlin, M., Johnson, M.P., Tomlinson, B.: Integrated Learning for Interactive Synthetic Characters. In: International Conference on Computer Graphics and Interactive Techniques (SIGGRAPH), pp. 417\u2013426 (2002)","DOI":"10.1145\/566570.566597"},{"key":"33_CR5","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1007694015589","volume":"43","author":"S. Dzeroski","year":"2001","unstructured":"Dzeroski, S., Raedt, L.D., Driessens, K.: Relational Reinforcement Learning. Machine Learning\u00a043, 7\u201352 (2001)","journal-title":"Machine Learning"},{"issue":"4","key":"33_CR6","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/s11370-012-0119-x","volume":"5","author":"E. Erdem","year":"2012","unstructured":"Erdem, E., Aker, E., Patoglu, V.: Answer Set Programming for Collaborative Housekeeping Robotics: Representation, Reasoning, and Execution. Intelligent Service Robotics\u00a05(4), 275\u2013291 (2012)","journal-title":"Intelligent Service Robotics"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Gelfond, M., Kahl, Y.: Knowledge Representation, Reasoning and the Design of Intelligent Agents. Cambridge University Press (2014)","DOI":"10.1017\/CBO9781139342124"},{"key":"33_CR8","unstructured":"Griffith, S., Subramanian, K., Scholz, J., Isbell, C., Thomaz, A.: Policy Shaping: Integrating Human Feedback with Reinforcement Learning. In: International Conference on Neural Information Processing Systems, Lake Tahoe, USA (2013)"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Kaplan, F., Oudeyer, P.-Y., Kubinyi, E., Miklosi, A.: Robotic Clicker Training. Robotics and Autonomous Systems\u00a038 (2002)","DOI":"10.1016\/S0921-8890(02)00168-9"},{"key":"33_CR10","unstructured":"Knox, W.B., Fasel, I., Stone Design, P.: principles for creating human-shapable agents. In: AAAI Spring 2009 Symposium on Agents that Learn from Human Teachers (2009)"},{"key":"33_CR11","unstructured":"Knox, W.B., Stone, P.: Tamer: Training an Agent Manually via Evaluative Reinforcement. In: International Conference on Development and Learning, ICDL (2008)"},{"key":"33_CR12","unstructured":"Knox, W.B., Stone, P.: Combining Manual Feedback with Subsequent MDP Reward Signals for Reinforcement Learning. In: International Conference on Autonomous Agents and Multiagent Systems, AAMAS (2010)"},{"issue":"3","key":"33_CR13","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1145\/1149114.1149117","volume":"7","author":"N. Leone","year":"2006","unstructured":"Leone, N., Pfeifer, G., Faber, W., Eiter, T., Gottlob, G., Perri, S., Scarcello, F.: The DLV System for Knowledge Representation and Reasoning. ACM Transactions on Computational Logic\u00a07(3), 499\u2013562 (2006)","journal-title":"ACM Transactions on Computational Logic"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Sridharan, M.: Augmented Reinforcement Learning for Interaction with Non-Expert Humans in Agent Domains. In: International Conference on Machine Learning Applications, ICMLA (December 2011)","DOI":"10.1109\/ICMLA.2011.37"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"33_CR16","unstructured":"Thomaz, A., Breazeal, C.: Reinforcement Learning with Human Teachers: Evidence of Feedback and Guidance with Implications for Learning Performance. In: National Conference on Artificial Intelligence, AAAI (2006)"},{"key":"33_CR17","first-page":"279","volume":"8","author":"C. Watkins","year":"1992","unstructured":"Watkins, C., Dayan, P.: Q-learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, S., Sridharan, M., Gelfond, M., Wyatt, J.: Integrating Probabilistic Graphical Models and Declarative Programming for Knowledge Representation and Reasoning in Robotics. In: Planning and Robotics (PlanRob) Workshop at ICAPS, Portsmouth, USA (2014)","DOI":"10.1007\/978-3-319-11973-1_41"}],"container-title":["Lecture Notes in Computer Science","Social Robotics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-11973-1_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T09:48:20Z","timestamp":1689587300000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-11973-1_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319119724","9783319119731"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-11973-1_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}