Optim4RL is a Jax framework of learning to optimize for reinforcement learning.

Personalizing Dialogue Agents via Meta-Learning

Task Generation Scheme for the Meta-Unsupervised Algorithm

Open-L2O: A Comprehensive and Reproducible Benchmark for Learning to Optimize Algorithms

A modular toolbox for meta-learning research with a focus on speed and reproducibility.

pytorch implementation of Optimization as a Model for Few-shot Learning

[NeurIPS 2020 Spotlight Oral] "Training Stronger Baselines for Learning to Optimize", Tianlong Chen*, Weiyi Zhang*, Jingyang Zhou, Shiyu Chang, Sijia Liu, Lisa Amini, Zhangyang Wang

[CVPR 2020] L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks

Learning to Learn: Gradient-free Optimization framework

A clean, lightweight and modularized PyTorch meta-learning library.

Chrome extension to create tasks based on the spaced repetition concept

Learnig Go with coding exercises

"Learning to learn by gradient descent by gradient descent "by PyTorch -- a simple re-implementation.

Learning to learn by gradient descent by gradient descent, Andrychowicz et al., NIPS 2016

Code for "Learning Inductive Biases with Simple Neural Networks" (Feinman & Lake, 2018).

Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning