{"type":"ScholarlyArticle","title":"Features, Projections, and Representation Change for Generalized Planning","authors":[{"name":"Blai Bonet","slug":"blai-bonet","given":"Blai","family":"Bonet","affiliation":"Universidad Simón Bolívar , Caracas , Venezuela"},{"name":"Hector Geffner","slug":"hector-geffner","given":"Hector","family":"Geffner","affiliation":"ICREA & Universitat Pompeu Fabra , Barcelona , Spain"}],"abstract":"Generalized planning is concerned with the characterization and computation of plans that solve many instances at once. In the standard formulation, a generalized plan is a mapping from fea- ture or observation histories into actions, assuming that the instances share a common pool of features and actions. This assumption, however, excludes the standard relational planning domains where actions and objects change across instances. In this work, we extend the standard formulation of generalized planning to such domains. This is achieved by projecting the actions over the features, resulting in a common set of abstract actions which can be tested for soundness and completeness, and which can be used for generating general policies such as “if the gripper is empty, pick the clear block above x and place it on the table” that achieve the goal clear(x) in any Blocksworld instance. In this policy, “pick the clear block above x” is an abstract action that may represent the action Unstack(a, b) in one situation and the action Unstack(b, c) in another. Transformations are also introduced for computing such policies by means of fully observable non-deterministic (FOND) planners. The value of generalized representations for learning general policies is also discussed.","doi":"10.24963/ijcai.2018/649","url":"https://ijcai.org/proceedings/2018/649","pdf":"https://ijcai.org/proceedings/2018/0649.pdf","markdown":"https://ijcai.org/proceedings/2018/649.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/649","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Planning and Scheduling","track":"Main track","number":649,"pages":{"first":4667,"last":4673},"keywords":["Knowledge Representation and Reasoning: Action, Change and Causality","Planning and Scheduling: Conformant;Contingent  planning","Planning and Scheduling: Planning Algorithms","Planning and Scheduling: Other approaches to planning"],"videos":[],"references":[{"position":1,"raw":"[Ballard et al., 1995] Dana H. Ballard, Mary M. Hayhoe, and Jeff B. Pelz. Memory representations in natural tasks. Journal of Cognitive Neuroscience, 7(1):66-80, 1995.","title":"Memory representations in natural tasks","authors":"H Dana, Mary M Ballard, Jeff B Hayhoe, Pelz","year":"1995","venue":"Journal of Cognitive Neuroscience","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ballard et al., 1997] Dana H. Ballard, Mary M. Hayhoe, Polly K. Pook, and Rajesh P. N. Rao. Deictic codes for the embodiment of cognition. Behavioral and Brain Sci- ences, 20(4):723-742, 1997.","title":"Deictic codes for the embodiment of cognition","authors":"H Dana, Mary M Ballard, Polly K Hayhoe, Pook, P N Rajesh, Rao","year":"1997","venue":"Behavioral and Brain Sciences","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Belle and Levesque, 2016] Vaishak Belle and Hector J. Levesque. Foundations for generalized planning in un- bounded stochastic domains. In KR, pages 380-389, 2016.","title":"Vaishak Belle and Hector J. Levesque. Foundations for generalized planning in unbounded stochastic domains","authors":"Belle, Levesque","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bonet et al., 2009] Blai Bonet, Hector Palacios, and Hector Geffner. Automatic derivation of memoryless policies and finite-state controllers using classical planners. In ICAPS, pages 34-41, 2009.","title":"Automatic derivation of memoryless policies and finite-state controllers using classical planners","authors":"Blai Bonet, Hector Palacios, Hector Geffner","year":"2009","venue":"ICAPS","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bonet et al., 2017] Blai Bonet, Giuseppe De Giacomo, Hec- tor Geffner, and Sasha Rubin. Generalized planning: Non- deterministic abstractions and trajectory constraints. In Proc. IJCAI, pages 873-879, 2017.","title":"Generalized planning: Nondeterministic abstractions and trajectory constraints","authors":"Blai Bonet, Giuseppe De Giacomo, Hector Geffner, Sasha Rubin","year":"2017","venue":"Proc. IJCAI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Boutilier et al., 2001] Craig Boutilier, Ray Reiter, and Bob Price. Symbolic dynamic programming for first-order MDPs. In IJCAI, volume 1, pages 690-700, 2001.","title":"Symbolic dynamic programming for first-order MDPs","authors":"Craig Boutilier, Ray Reiter, Bob Price","year":"2001","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2001/95"},{"position":7,"raw":"[Chapman, 1989] David Chapman. Penguins can make cake. AI magazine, 10(4):45-50, 1989.","title":"Penguins can make cake","authors":"David Chapman","year":"1989","venue":"AI magazine","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Cimatti et al., 2003] Alessandro Cimatti, Marco Pistore, Marco Roveri, and Paolo Traverso. Weak, strong, and strong cyclic planning via symbolic model checking. Arti- ficial Intelligence, 147(1-2):35-84, 2003.","title":"Weak, strong, and strong cyclic planning via symbolic model checking","authors":"Alessandro Cimatti, Marco Pistore, Marco Roveri, Paolo Traverso","year":"2003","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fern et al., 2006] Alan Fern, Sung Wook Yoon, and Robert Givan. Approximate policy iteration with a policy lan- guage bias: Solving relational markov decision processes. JAIR, 25:75-118, 2006.","title":"Approximate policy iteration with a policy language bias: Solving relational markov decision processes","authors":"Alan Fern, Sung Wook Yoon, Robert Givan","year":"2006","venue":"JAIR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Geffner and Geffner, 2018] Tomas Geffner and Hector Geffner. Compact policies for non-deterministic fully observable planning as SAT. In Proc. ICAPS, 2018. To appear.","title":"Compact policies for non-deterministic fully observable planning as SAT","authors":"Geffner Geffner, Tomas Geffner, Hector Geffner","year":"2018","venue":"Proc. ICAPS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Groshev et al., 2017] Edward Groshev, Maxwell Goldstein, Aviv Tamar, Siddharth Srivastava, and Pieter Abbeel. Learning generalized reactive policies using deep neural networks. arXiv preprint arXiv:1708.07280, 2017.","title":"Learning generalized reactive policies using deep neural networks","authors":"Edward Groshev, Maxwell Goldstein, Aviv Tamar, Siddharth Srivastava, Pieter Abbeel","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Helmert, 2002] Malte Helmert. Decidability and undecid- ability results for planning with numerical state variables. In Proc. ICAPS, pages 44-53, 2002.","title":"Decidability and undecidability results for planning with numerical state variables","authors":"Malte Helmert, Helmert","year":"2002","venue":"Proc. ICAPS","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hu and De Giacomo, 2011] Yuxiao Hu and Giuseppe De Giacomo. Generalized planning: Synthesizing plans that work for multiple environments. In IJCAI, pages 918-923, 2011.","title":"Generalized planning: Synthesizing plans that work for multiple environments","authors":"De Hu, ; Yuxiao Giacomo, Giuseppe Hu, Giacomo De","year":"2011","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2011/159"},{"position":14,"raw":"[Lipovetzky and Geffner, 2012] Nir Lipovetzky and Hector Geffner. Width and serialization of classical planning problems. In Proc. ECAI, pages 540-545, 2012.","title":"Width and serialization of classical planning problems","authors":"Geffner Lipovetzky, Nir Lipovetzky, Hector Geffner","year":"2012","venue":"Proc. ECAI","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Martín and Geffner, 2004] Mario Martín and Hector Geffner. Learning generalized policies from planning examples using concept languages. Applied Intelligence, 20(1):9-19, 2004.","title":"Learning generalized policies from planning examples using concept languages","authors":"Geffner Martín, Mario Martín, Hector Geffner","year":"2004","venue":"Applied Intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Mattmüller et al., 2010] Robert Mattmüller, Manuela Or- tlieb, Malte Helmert, and Pascal Bercher. Pattern database heuristics for fully observable nondeterministic planning. In Proc. ICAPS, pages 105-112, 2010.","title":"Pattern database heuristics for fully observable nondeterministic planning","authors":"Robert Mattmüller, Manuela Ortlieb, Malte Helmert, Pascal Bercher","year":"2010","venue":"Proc. ICAPS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Mirowski et al., 2016] Piotr Mirowski, Razvan Pascanu, Fabio Viola, Hubert Soyer, Andrew J. Ballard, Andrea Banino, Misha Denil, Ross Goroshin, Laurent Sifre, Ko- ray Kavukcuoglu, Dharshan Kumaran, and Raia Hadsell. Learning to navigate in complex environments. arXiv preprint arXiv:1611.03673, 2016.","title":"Learning to navigate in complex environments","authors":"Piotr Mirowski, Razvan Pascanu, Fabio Viola, Hubert Soyer, Andrew J Ballard, Andrea Banino, Misha Denil, Ross Goroshin, Laurent Sifre, Koray Kavukcuoglu, Dharshan Kumaran, Raia Hadsell","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Segovia et al., 2016] Javier Segovia, Sergio Jiménez, and Anders Jonsson. Generalized planning with procedural do- main control knowledge. In Proc. ICAPS, pages 285-293, 2016.","title":"Generalized planning with procedural domain control knowledge","authors":"Javier Segovia, Sergio Jiménez, Anders Jonsson","year":"2016","venue":"Proc. ICAPS","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Srivastava et al., 2008] Siddharth Srivastava, Neil Immer- man, and Shlomo Zilberstein. Learning generalized plans using abstract counting. In AAAI, pages 991-997, 2008.","title":"Learning generalized plans using abstract counting","authors":"Siddharth Srivastava, Neil Immerman, Shlomo Zilberstein","year":"2008","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Srivastava et al., 2011a] Siddharth Srivastava, Neil Immer- man, and Shlomo Zilberstein. A new representation and associated algorithms for generalized planning. Artificial Intelligence, 175(2):615-647, 2011.","title":"a] Siddharth Srivastava, Neil Immerman, and Shlomo Zilberstein. A new representation and associated algorithms for generalized planning","authors":"Srivastava","year":"2011","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Srivastava et al., 2011b] Siddharth Srivastava, Shlomo Zil- berstein, Neil Immerman, and Hector Geffner. Qualitative numeric planning. In AAAI, pages 1010-1016, 2011.","title":"Qualitative numeric planning","authors":"Srivastava","year":"2011","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[van Otterlo, 2012] Martijn van Otterlo. Solving relational and first-order logical markov decision processes: A sur- vey. In Reinforcement Learning, pages 253-292. Springer, 2012.","title":"Solving relational and first-order logical markov decision processes: A survey","authors":"Martijn Van Otterlo","year":"2012","venue":"Reinforcement Learning","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2008] Chenggang Wang, Saket Joshi, and Roni Khardon. First order decision diagrams for relational MDPs. Journal of Artificial Intelligence Research, 31:431-472, 2008.","title":"First order decision diagrams for relational MDPs","authors":"Chenggang Wang, Saket Joshi, Roni Khardon","year":"2008","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":"/proceedings/2007/177"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}