Playgol：通过游戏学习程序
Playgol: learning programs through play
摘要：
孩子们通过游戏学习。我们介绍了通过游戏学习程序的类似想法。在这种方法中，程序诱导系统（学习者）被赋予一组任务和初始背景知识。在解决任务之前，学习者进入一个无监督的游戏阶段，在那里它创建自己的任务来解决，尝试解决它们，并将任何解决方案（程序）保存到背景知识中。在游戏阶段完成后，学习者进入监督构建阶段，在那里它试图解决用户提供的任务，并可以重用在游戏中学习到的解决方案。这个想法是，玩允许学习者发现自己的可重用的通用程序，然后可以帮助解决用户提供的任务。我们认为游戏可以提高学习成绩。我们发现，播放可以降低目标概念的文本复杂性，这反过来又降低了学习者的样本复杂性。我们实现了我们的想法在Playgol，一个新的归纳逻辑程序设计系统。我们实验测试我们的要求在两个领域：机器人规划和现实世界的字符串转换。我们的实验结果表明，玩可以大大提高学习成绩。我们认为，玩的想法（或者更详细地说，监督程序诱导的无监督引导）是一个重要的贡献，开发程序诱导方法，自我发现BK的问题。
英文摘要：
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 tasks and initial background knowledge. Before solving the tasks, the learner enters an unsupervised playing stage where it creates its own tasks to solve, tries to solve them, and saves any solutions (programs) to the background knowledge. After the playing stage is finished, the learner enters the supervised building stage where it tries to solve the user-supplied 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 user-supplied 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. We think that the idea of playing (or, more verbosely, unsupervised bootstrapping for supervised program induction) is an important contribution to the problem of developing program induction approaches that self-discover BK.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
