{"type":"ScholarlyArticle","title":"Playgol: Learning Programs Through Play","authors":[{"name":"Andrew Cropper","slug":"andrew-cropper","given":"Andrew","family":"Cropper","affiliation":"University of Oxford"}],"abstract":"Children learn though play. We introduce the analogous idea of learning programs through play. In this approach, a program induction system (the learner) is given a set of user-supplied build tasks and initial background knowledge (BK). Before solving the build tasks, the learner enters an unsupervised playing stage where it creates its own play tasks to solve, tries to solve them, and saves any solutions (programs) to the BK. After the playing stage is finished, the learner enters the supervised building stage where it tries to solve the build tasks and can reuse solutions learnt whilst playing. The idea is that playing allows the learner to discover reusable general programs on its own which can then help solve the build tasks. We claim that playing can improve learning performance. We show that playing can reduce the textual complexity of target concepts which in turn reduces the sample complexity of a learner. We implement our idea in Playgol, a new inductive logic programming system. We experimentally test our claim on two domains: robot planning and real-world string transformations. Our experimental results suggest that playing can substantially improve learning performance.","doi":"10.24963/ijcai.2019/841","url":"https://ijcai.org/proceedings/2019/841","pdf":"https://ijcai.org/proceedings/2019/0841.pdf","markdown":"https://ijcai.org/proceedings/2019/841.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/841","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Understanding Intelligence and Human-level AI in the New Machine Learning era","track":"Understanding Intelligence and Human-level AI in the New Machine Learning era","number":841,"pages":{"first":6074,"last":6080},"keywords":["Special Track on Understanding Intelligence and Human-level AI in the New Machine Learning era: Machine Learning and Classical AI (Special Track on Human AI and Machine Learning)"],"videos":[],"references":[{"position":1,"raw":"[Balog et al., 2017] Matej Balog, Alexander L. Gaunt, Marc Brockschmidt, Sebastian Nowozin, and Daniel Tarlow. Deepcoder: Learning to write programs. In ICLR. OpenRe- view.net, 2017.","title":"Deepcoder: Learning to write programs","authors":"Matej Balog, Alexander L Gaunt, Marc Brockschmidt, Sebastian Nowozin, Daniel Tarlow","year":"2017","venue":"ICLR. OpenReview.net","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bengio et al., 2009] Yoshua Bengio, Jérôme Louradour, Ro- nan Collobert, and Jason Weston. Curriculum learning. In ICML 2019, volume 382, pages 41-48. ACM, 2009.","title":"Curriculum learning","authors":"Yoshua Bengio, Jérôme Louradour, Ronan Collobert, Jason Weston","year":"2009","venue":"ICML 2019","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Blockeel and Raedt, 1998] Hendrik Blockeel and Luc De Raedt. Top-down induction of first-order logical decision trees. Artif. Intell., 101(1-2):285-297, 1998.","title":"Top-down induction of first-order logical decision trees","authors":"Raedt Blockeel, Hendrik Blockeel, Luc De, Raedt","year":"1998","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Blumer et al., 1989] Anselm Blumer, Andrzej Ehrenfeucht, David Haussler, and Manfred K. Warmuth. Learnability and the vapnik-chervonenkis dimension. J. ACM, 36(4):929- 965, 1989.","title":"Learnability and the vapnik-chervonenkis dimension","authors":"Anselm Blumer, Andrzej Ehrenfeucht, David Haussler, Manfred K Warmuth","year":"1989","venue":"J. ACM","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cropper and Muggleton, 2016a] Andrew Cropper and Stephen H. Muggleton. Learning higher-order logic programs through abstraction and invention. In IJCAI 2016, pages 1418-1424. IJCAI/AAAI Press, 2016.","title":"Learning higher-order logic programs through abstraction and invention","authors":"Muggleton Cropper, Andrew Cropper, Stephen H Muggleton","year":"2016","venue":"IJCAI 2016","doi":null,"url":null,"internal_url":"/proceedings/2016/204"},{"position":6,"raw":"[Cropper and Muggleton, 2016b] Andrew Cropper and Stephen H. Muggleton. Metagol system. https://github.com/metagol/metagol, 2016.","title":"Metagol system","authors":"Muggleton Cropper, Andrew Cropper, Stephen H Muggleton","year":"2016","venue":null,"doi":null,"url":"https://github.com/metagol/metagol,2016","internal_url":null},{"position":7,"raw":"[Cropper and Muggleton, 2018] Andrew Cropper and Stephen H. Muggleton. Learning efficient logic programs. Machine Learning, Apr 2018.","title":"Learning efficient logic programs","authors":"Andrew Cropper, Stephen H Muggleton","year":"2018","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Cropper, 2017] Andrew Cropper. Efficiently learning effi- cient programs. PhD thesis, Imperial College London, UK, 2017.","title":"Efficiently learning efficient programs","authors":"Andrew Cropper","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Dechter et al., 2013] Eyal Dechter, Jonathan Malmaud, Ryan P. Adams, and Joshua B. Tenenbaum. Bootstrap learning via modular concept discovery. In IJCAI 2013, pages 1302-1309. IJCAI/AAAI, 2013.","title":"Bootstrap learning via modular concept discovery","authors":"Eyal Dechter, Jonathan Malmaud, Ryan P Adams, Joshua B Tenenbaum","year":"2013","venue":"IJCAI 2013","doi":null,"url":null,"internal_url":"/proceedings/2013/196"},{"position":10,"raw":"[Dietterich et al., 2008] Thomas G. Dietterich, Pedro M. Domingos, Lise Getoor, Stephen Muggleton, and Prasad Tadepalli. Structured machine learning: the next ten years. Machine Learning, 73(1):3-23, 2008.","title":"Structured machine learning: the next ten years","authors":"G Thomas, Pedro M Dietterich, Lise Domingos, Stephen Getoor, Prasad Muggleton, Tadepalli","year":"2008","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Dumancic and Blockeel, 2017] Sebastijan Dumancic and Hendrik Blockeel. Clustering-based relational unsuper- vised representation learning with an explicit distributed representation. In Carles Sierra, editor, IJCAI 2017, pages 1631-1637. ijcai.org, 2017.","title":"Sebastijan Dumancic and Hendrik Blockeel. Clustering-based relational unsupervised representation learning with an explicit distributed representation","authors":"Blockeel Dumancic","year":"2017","venue":"IJCAI 2017","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ellis and Gulwani, 2017] Kevin Ellis and Sumit Gulwani. Learning to learn programs from examples: Going beyond program structure. In IJCAI 2017, pages 1638-1645. ij- cai.org, 2017.","title":"Learning to learn programs from examples: Going beyond program structure","authors":"Kevin Ellis, Sumit Gulwani","year":"2017","venue":"IJCAI 2017","doi":null,"url":null,"internal_url":"/proceedings/2017/227"},{"position":13,"raw":"[Ellis et al., 2018a] Kevin Ellis, Lucas Morales, Mathias Sablé-Meyer, Armando Solar-Lezama, and Josh Tenen- baum. Learning libraries of subroutines for neurally-guided bayesian program induction. In NeurIPS 2018, pages 7816- 7826, 2018.","title":"Learning libraries of subroutines for neurally-guided bayesian program induction","authors":"Ellis","year":"2018","venue":"NeurIPS 2018","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ellis et al., 2018b] Kevin Ellis, Daniel Ritchie, Armando Solar-Lezama, and Josh Tenenbaum. Learning to infer graphics programs from hand-drawn images. In NeurIPS 2018, pages 6062-6071, 2018.","title":"Learning to infer graphics programs from hand-drawn images","authors":"Ellis","year":"2018","venue":"NeurIPS 2018","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Evans and Grefenstette, 2018] Richard Evans and Edward Grefenstette. Learning explanatory rules from noisy data. J. Artif. Intell. Res., 61:1-64, 2018.","title":"Learning explanatory rules from noisy data","authors":"Grefenstette Evans, Richard Evans, Edward Grefenstette","year":"2018","venue":"J. Artif. Intell. Res","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Gulwani, 2011] Sumit Gulwani. Automating string process- ing in spreadsheets using input-output examples. In POPL 2011, pages 317-330, 2011.","title":"Automating string processing in spreadsheets using input-output examples","authors":"Sumit Gulwani","year":"2011","venue":"POPL 2011","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Law et al., 2014] Mark Law, Alessandra Russo, and Krysia Broda. Inductive learning of answer set programs. In JELIA 2014, pages 311-325, 2014.","title":"Inductive learning of answer set programs","authors":"Mark Law, Alessandra Russo, Krysia Broda","year":"2014","venue":"JELIA 2014","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Lenat, 1977] Douglas B. Lenat. Automated theory formation in mathematics. In Raj Reddy, editor, Proceedings of the 5th International Joint Conference on Artificial Intelligence. Cambridge, MA, USA, August 22-25, 1977, pages 833-842.","title":"Automated theory formation in mathematics","authors":"B Douglas, Lenat","year":"1977","venue":"Proceedings of the 5th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/1977/198"},{"position":19,"raw":"William Kaufmann, 1977.","title":null,"authors":"William Kaufmann","year":"1977","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Lin et al., 2014] Dianhuan Lin, Eyal Dechter, Kevin Ellis, Joshua B. Tenenbaum, and Stephen Muggleton. Bias refor- mulation for one-shot function induction. In ECAI 2014, pages 525-530, 2014.","title":"Bias reformulation for one-shot function induction","authors":"Lin","year":"2014","venue":"ECAI 2014","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Mitchell, 1997] Tom M. Mitchell. Machine learning. Mc- Graw Hill series in computer science. McGraw-Hill, 1997.","title":"Machine learning","authors":"Tom M Mitchell","year":"1997","venue":"Mc-Graw Hill series in computer science","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Muggleton et al., 2014] Stephen H. Muggleton, Dianhuan Lin, Niels Pahlavi, and Alireza Tamaddoni-Nezhad. Meta- interpretive learning: application to grammatical inference. Machine Learning, 94(1):25-49, 2014.","title":"Metainterpretive learning: application to grammatical inference","authors":"H Stephen, Dianhuan Muggleton, Niels Lin, Alireza Pahlavi, Tamaddoni-Nezhad","year":"2014","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Muggleton et al., 2015] Stephen H. Muggleton, Dianhuan Lin, and Alireza Tamaddoni-Nezhad. Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited. Machine Learning, 100(1):49-73, 2015.","title":"Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited","authors":"H Stephen, Dianhuan Muggleton, Alireza Lin, Tamaddoni-Nezhad","year":"2015","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Raedt, 2008] Luc De Raedt. Logical and relational learning. Cognitive Technologies. Springer, 2008.","title":"Logical and relational learning","authors":"Luc Raedt, Raedt De","year":"2008","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Schüller and Benz, 2018] Peter Schüller and Mishal Benz. Best-effort inductive logic programming via fine-grained cost-based hypothesis generation -the inspire system at the inductive logic programming competition. Machine Learning, 107(7):1141-1169, 2018.","title":"Best-effort inductive logic programming via fine-grained cost-based hypothesis generation -the inspire system at the inductive logic programming competition","authors":"Peter Schüller, Mishal Benz","year":"2018","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Schulz et al., 2007] Laura E Schulz, Alison Gopnik, and Clark Glymour. Preschool children learn about causal struc- ture from conditional interventions. Developmental science, 10(3):322-332, 2007.","title":"Preschool children learn about causal structure from conditional interventions","authors":"Laura E Schulz, Alison Gopnik, Clark Glymour","year":"2007","venue":"Developmental science","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Sim and Xu, 2017] Zi L Sim and Fei Xu. Learning higher- order generalizations through free play: Evidence from 2-and 3-year-old children. Developmental psychology, 53(4):642, 2017.","title":"Learning higherorder generalizations through free play: Evidence from 2-and 3-year-old children","authors":"L Zi, Fei Sim, Xu","year":"2017","venue":"Developmental psychology","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Sim et al., 2017] Zi Lin Sim, Kuldeep K. Mahal, and Fei Xu. Is play better than direct instruction? learning about causal systems through play. In CogSci 2017, 2017.","title":"Is play better than direct instruction? learning about causal systems through play","authors":"Lin Zi, Kuldeep K Sim, Fei Mahal, Xu","year":"2017","venue":"CogSci 2017","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Thrun and Pratt, 2012] Sebastian Thrun and Lorien Pratt. Learning to learn. Springer Science & Business Media, 2012.","title":"Sebastian Thrun and Lorien Pratt","authors":"Pratt Thrun","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}