Playgol: Learning Programs Through Play
Open accessAbstract
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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Because of its symbolic representation, ILP naturally supports lifelong and transfer learning.
“By contrast, because of its symbolic representation, ILP naturally supports lifelong and transfer learning (Torrey et al., 2007; Cropper, 2019), which is considered essential for human-like AI (Lake et al., 2016).”
From Inductive Logic Programming At 30: A New Introduction (2022) · cites this paper as Cropper, 2019
The Related Work section (page unavailable) says that ILP meta-learning saves learned programs as background knowledge for reuse on unsolved tasks, supporting learning over time and transfer between tasks. The paper does not attribute that capability specifically to ILP’s symbolic representation or establish it as a natural property of ILP generally; it describes particular approaches that implement it. (LLM, conf=0.83)
Experimental — accuracy not yet measuredPredicate invention helps reduce the size of target programs, which in turn reduces sample complexity and improves predictive accuracy.
“Predicate invention has been shown to help reduce the size of target programs, which in turns reduces sample complexity and improves predictive accuracy (Cropper 2019; Dumancic et al. 2019).”
From Learning programs by learning from failures (2021) · cites this paper as Cropper 2019
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 27 · Cited by 30
Research works printed but not linked: 21
- Matej Balog, Alexander L. Gaunt, Marc Brockschmidt, Sebastian Nowozin, and Daniel Tarlow. Deepcoder: Learning to write programs. In ICLR. OpenRe- view.net, 2017.
- 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.
- Anselm Blumer, Andrzej Ehrenfeucht, David Haussler, and Manfred K. Warmuth. Learnability and the vapnik-chervonenkis dimension. J. ACM, 36(4):929- 965, 1989.
- 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.
- Andrew Cropper. Efficiently learning effi- cient programs. PhD thesis, Imperial College London, UK, 2017.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- Sumit Gulwani. Automating string process- ing in spreadsheets using input-output examples. In POPL 2011, pages 317-330, 2011.
- 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.
- 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.
- Tom M. Mitchell. Machine learning. Mc- Graw Hill series in computer science. McGraw-Hill, 1997.
- 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.
- Raedt, 2008] Luc De Raedt. Logical and relational learning. Cognitive Technologies. Springer, 2008.
- 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.
- 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.
- 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.
- Thrun and Pratt, 2012] Sebastian Thrun and Lorien Pratt. Learning to learn. Springer Science & Business Media, 2012.
- Authors
- Cropper, A.
- Affiliations
- University of Oxford (GB)
- Corresponding author
- Cropper, Andrew
- ORCID
- Cropper, Andrew
- Venue
- Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
- Published
- 2019-08
- Pages
- 6074-6080
- OpenAlex
- W2936168870
- Cited by
- 30
- References
- 27
- Citations by year
- 2026: 1 · 2025: 1 · 2024: 1 · 2023: 7 · 2022: 1 · 2021: 11 · 2020: 7
- FWCI
- 1.82
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Joint Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Computer Science › Artificial Intelligence › Evolutionary Algorithms and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Keywords
- program induction, inductive logic programming, unsupervised learning, prior knowledge, sample complexity, text complexity, robot planning, string transformation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
