Reptile：可扩展的元学习算法
Reptile: A scalable meta-learning algorithm
OpenAI 开发了名为 Reptile 的元学习算法，该算法通过重复采样任务、在任务上执行随机梯度下降并更新初始参数，使其向最终参数学习。Reptile 是将最短下降算法应用于元学习环境，与仅需要黑盒访问优化器（如 SGD 或 Adam）的第一阶 MAML 算法在数学上相似，具有相似的计算效率和性能。
We’ve developed a simple meta-learning algorithm called Reptile which works by repeatedly sampling a task, performing stochastic gradient descent on it, and updating the initial parameters towards the final parameters learned on that task. Reptile is the application of the Shortest Descent algorithm to the meta-learning setting, and is mathematically similar to first-order MAML (which is a version of the well-known MAML algorithm) that only needs black-box access to an optimizer such as SGD or Adam, with similar computational efficiency and performance.
来源：OpenAI News · openai.com