{"type":"ScholarlyArticle","title":"Efficient, Safe, and Probably Approximately Complete Learning of Action Models","authors":[{"name":"Roni Stern","slug":"roni-stern","given":"Roni","family":"Stern","affiliation":"Ben Gurion University of the Negev Be'er Sheva , Israel"},{"name":"Brendan Juba","slug":"brendan-juba","given":"Brendan","family":"Juba","affiliation":"Washington University in St. Louis St . Louis , MO , 63130 USA"}],"abstract":"In this paper we explore the theoretical boundaries of planning in a setting where no model of the agent's actions is given. Instead of an action model, a set of successfully executed plans are given and the task is to generate a plan that is safe, i.e., guaranteed to achieve the goal without failing. \r\nTo this end, we show how to learn a conservative model of the world \r\nin which actions are guaranteed to be applicable. \r\nThis conservative model is then given to an off-the-shelf classical planner, \r\nresulting in a plan that is guaranteed to achieve the goal. \r\nHowever, this reduction from a model-free planning to a \r\nmodel-based planning is not complete: in some cases \r\na plan will not be found even when such exists. \r\nWe analyze the relation between the number of observed plans \r\nand the likelihood that our conservative approach will indeed fail to solve a solvable problem. Our analysis show that the number of trajectories needed scales gracefully.","doi":"10.24963/ijcai.2017/615","url":"https://ijcai.org/proceedings/2017/615","pdf":"https://ijcai.org/proceedings/2017/0615.pdf","markdown":"https://ijcai.org/proceedings/2017/615.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/615","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Planning and Scheduling","track":"Main track","number":615,"pages":{"first":4405,"last":4411},"keywords":["Planning and Scheduling: Theoretical Foundations of Planning","Planning and Scheduling: Conformant/Contingent planning","Planning and Scheduling: Planning with Incomplete information"],"videos":[],"references":[{"position":1,"raw":"[Bäckström and Nebel, 1995] Christer Bäckström and Bern- hard Nebel. Complexity results for SAS+ planning. Com- putational Intelligence, 11(4):625-655, 1995.","title":"Christer Bäckström and Bernhard Nebel","authors":"Nebel Bäckström","year":"1995","venue":"Computational Intelligence","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cavalcanti et al., 2007] Adriano Cavalcanti, Bijan Shirin- zadeh, Robert A Freitas Jr, and Tad Hogg. Nanorobot architecture for medical target identification. Nanotech- nology, 19(1):015103, 2007.","title":"Nanorobot architecture for medical target identification","authors":"Adriano Cavalcanti, Bijan Shirinzadeh, Robert A Freitas, Tad Hogg","year":"2007","venue":"Nanotechnology","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cresswell et al., 2013] Stephen N. Cresswell, Thomas L. McCluskey, and Margaret M. West. Acquiring planning domain models using LOCM. The Knowledge Engineer- ing Review, 28(02):195-213, 2013.","title":"Acquiring planning domain models using LOCM","authors":"Stephen N Cresswell, Thomas L Mccluskey, Margaret M West","year":"2013","venue":"The Knowledge Engineering Review","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Daniely and Shalev-Shwartz, 2016] Amit Daniely and Shai Shalev-Shwartz. Complexity theoretic limtations on learn- ing DNF's. In Proceedings of the 29th Conference on Computational Learning Theory, volume 49 of JMLR Workshops and Conference Proceedings, pages 1-16. 2016.","title":"Complexity theoretic limtations on learning DNF's","authors":"Amit Daniely, Shai Shalev-Shwartz","year":"2016","venue":"Proceedings of the 29th Conference on Computational Learning Theory","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Fikes and Nilsson, 1971] Richard E Fikes and Nils J Nils- son. STRIPS: A new approach to the application of the- orem proving to problem solving. Artificial intelligence, 2(3-4):189-208, 1971.","title":"STRIPS: A new approach to the application of theorem proving to problem solving","authors":"E Richard, Nils J Fikes, Nilsson","year":"1971","venue":"Artificial intelligence","doi":null,"url":null,"internal_url":"/proceedings/1971/63"},{"position":6,"raw":"[Jiménez et al., 2013] Sergio Jiménez, Fernando Fernández, and Daniel Borrajo. Integrating planning, execution, and learning to improve plan execution. Computational Intel- ligence, 29(1):1-36, 2013.","title":"Integrating planning, execution, and learning to improve plan execution","authors":"Sergio Jiménez, Fernando Fernández, Daniel Borrajo","year":"2013","venue":"Computational Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Kakade, 2003] Sham M. Kakade. On the sample complex- ity of reinforcement learning. PhD thesis, University of London, 2003.","title":"On the sample complexity of reinforcement learning","authors":"M Sham, Kakade","year":"2003","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kearns and Valiant, 1994] Michael Kearns and Leslie Valiant. Cryptographic limitations on learning boolean formulae and finite automata. Journal of the ACM (JACM), 41(1):67-95, 1994.","title":"Cryptographic limitations on learning boolean formulae and finite automata","authors":"Michael Kearns, Leslie Valiant","year":"1994","venue":"Journal of the ACM (JACM)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kearns et al., 2002] Michael Kearns, Yishay Mansour, and Andrew Ng. A sparse sampling algorithm for near-optimal planning in large Markov decision processes. Mach. Learn., 49(2):193-208, 2002.","title":"A sparse sampling algorithm for near-optimal planning in large Markov decision processes","authors":"Michael Kearns, Yishay Mansour, Andrew Ng","year":"2002","venue":"Mach. Learn","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Levine and DeJong, 2006] Geoffrey Levine and Gerald De- Jong. Explanation-based acquisition of planning opera- tors. In ICAPS, pages 152-161, 2006.","title":"Explanation-based acquisition of planning operators","authors":"Dejong Levine, Geoffrey Levine, Gerald De-Jong","year":"2006","venue":"ICAPS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Littman, 1994] Michael L. Littman. Memoryless policies: Theoretical limitations and practical results. In From An- imals to Animats 3: Proceedings of the Third Interna- tional Conference on Simulation of Adaptive Behavior, volume 3, page 238. MIT Press, 1994.","title":"Memoryless policies: Theoretical limitations and practical results","authors":"L Michael, Littman","year":"1994","venue":"From Animals to Animats 3: Proceedings of the Third International Conference on Simulation of Adaptive Behavior","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[McDermott et al., 1998] Drew McDermott, Malik Ghallab, Adele Howe, Craig Knoblock, Ashwin Ram, Manuela Veloso, Daniel Weld, and David Wilkins. PDDL-the plan- ning domain definition language. Technical report, AIPS '98 -The Planning Competition Committee, 1998.","title":"PDDL-the planning domain definition language","authors":"Drew Mcdermott, Malik Ghallab, Adele Howe, Craig Knoblock, Ashwin Ram, Manuela Veloso, Daniel Weld, David Wilkins","year":"1998","venue":"Technical report, AIPS '98 -The Planning Competition Committee","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Meuleau et al., 1999] Nicolas Meuleau, Kee-Eung Kim, Leslie Pack Kaelbling, and Anthony R. Cassandra. Solv- ing POMDPs by searching the space of finite policies. In Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence, pages 417-426.","title":"Solving POMDPs by searching the space of finite policies","authors":"Nicolas Meuleau, Kee-Eung Kim, Leslie Pack Kaelbling, Anthony R Cassandra","year":null,"venue":"Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Mourão et al., 2012] Kira Mourão, Luke S Zettlemoyer, Ronald Petrick, and Mark Steedman. Learning STRIPS operators from noisy and incomplete observations. In UAI, pages 614-623, 2012.","title":"Learning STRIPS operators from noisy and incomplete observations","authors":"Kira Mourão, Luke S Zettlemoyer, Ronald Petrick, Mark Steedman","year":"2012","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Nebel, 2000] Bernhard Nebel. On the compilability and expressive power of propositional planning formalisms. Journal of Artificial Intelligence Research, 12:271-315, 2000.","title":"On the compilability and expressive power of propositional planning formalisms","authors":"Bernhard Nebel","year":"2000","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Valiant, 1984] Leslie G. Valiant. A theory of the learnable. Communications of the ACM, 18(11):1134-1142, 1984.","title":"A theory of the learnable","authors":"Leslie G Valiant","year":"1984","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Vapnik and Chervonenkis, 1971] V. Vapnik and A. Chervo- nenkis. On the uniform convergence of relative frequen- cies of events to their probabilities. Theory of Probability and its Applications, 16(2):264-280, 1971.","title":"On the uniform convergence of relative frequencies of events to their probabilities","authors":"V Vapnik, A Chervonenkis","year":"1971","venue":"Theory of Probability and its Applications","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Walsh and Littman, 2008] Thomas J. Walsh and Michael L. Littman. Efficient learning of action schemas and web- service descriptions. In the National Conference on Artifi- cial Intelligence (AAAI), pages 714-719, 2008.","title":"Efficient learning of action schemas and webservice descriptions","authors":"Thomas J Walsh, Michael L Littman","year":"2008","venue":"the National Conference on Artificial Intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Wang, 1994] Xuemei Wang. Learning planning operators by observation and practice. In the International Confer- ence on Artificial Intelligence Planning Systems (AIPS), pages 335-340, 1994.","title":"Learning planning operators by observation and practice","authors":"Xuemei Wang","year":"1994","venue":"the International Conference on Artificial Intelligence Planning Systems (AIPS)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Wang, 1995] Xuemei Wang. Learning by observation and practice: An incremental approach for planning operator acquisition. In ICML, pages 549-557, 1995.","title":"Learning by observation and practice: An incremental approach for planning operator acquisition","authors":"Xuemei Wang","year":"1995","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Yang et al., 2007] Qiang Yang, Kangheng Wu, and Yunfei Jiang. Learning action models from plan examples us- ing weighted MAX-SAT. Artificial Intelligence, 171(2- 3):107-143, 2007.","title":"Learning action models from plan examples using weighted MAX-SAT","authors":"Qiang Yang, Kangheng Wu, Yunfei Jiang","year":"2007","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}