论文标题
通过编码为神经网络的自我发明的实验一次学习一个抽象的位
Learning One Abstract Bit at a Time Through Self-Invented Experiments Encoded as Neural Networks
论文作者
论文摘要
科学中有两件事：（a）找到给定问题的答案，以及（b）提出好问题。我们的人工科学家不仅通过提出通过潜在的复杂且耗时的实验来验证或伪造的假设，包括与数学家类似的思想实验，还通过提出要验证或伪造的假设来回答新问题。尽管人工科学家扩大了知识，但它仍然偏向最简单，最不昂贵的实验，这些实验仍然具有令人惊讶的结果，直到它们变得无聊。我们对自动生成有趣的实验进行了经验分析。在第一个环境中，我们在提供强化的环境中调查了自我发明的实验，并表明它们会导致有效的探索。在第二个环境中，纯思想实验是作为神经实验发生器产生的复发性神经网络的权重实施的。最初有趣的思想实验可能会随着时间的流逝而变得无聊。
There are two important things in science: (A) Finding answers to given questions, and (B) Coming up with good questions. Our artificial scientists not only learn to answer given questions, but also continually invent new questions, by proposing hypotheses to be verified or falsified through potentially complex and time-consuming experiments, including thought experiments akin to those of mathematicians. While an artificial scientist expands its knowledge, it remains biased towards the simplest, least costly experiments that still have surprising outcomes, until they become boring. We present an empirical analysis of the automatic generation of interesting experiments. In the first setting, we investigate self-invented experiments in a reinforcement-providing environment and show that they lead to effective exploration. In the second setting, pure thought experiments are implemented as the weights of recurrent neural networks generated by a neural experiment generator. Initially interesting thought experiments may become boring over time.
