Playgol: Learning Programs Through Play

Playgol: Learning Programs Through Play

Andrew Cropper

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Understanding Intelligence and Human-level AI in the New Machine Learning era. Pages 6074-6080. https://doi.org/10.24963/ijcai.2019/841

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.
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)