# Online Learning of a Memory for Learning Rates

arXiv: https://arxiv.org/abs/1709.06709 · HTML: https://mlsanity.com/paper/1709.06709/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2017.

## Built on by (most cited first, 4 of 4)

- [Curiosity-driven Intuitive Physics Learning](https://mlsanity.com/paper/2105.07426/) (2021)
- [Model Based Meta Learning of Critics for Policy Gradients](https://mlsanity.com/paper/2204.02210/) (2022)
- [Implicit Training of Energy Model for Structure Prediction](https://mlsanity.com/paper/2211.11649/) (2022)
- [Stepsize Learning for Policy Gradient Methods in Contextual Markov Decision Processes](https://mlsanity.com/paper/2306.07741/) (2023)

## Abstract (arXiv)

The promise of learning to learn for robotics rests on the hope that by extracting some information about the learning process itself we can speed up subsequent similar learning tasks. Here, we introduce a computationally efficient online meta-learning algorithm that builds and optimizes a memory model of the optimal learning rate landscape from previously observed gradient behaviors. While performing task specific optimization, this memory of learning rates predicts how to scale currently observed gradients. After applying the gradient scaling our meta-learner updates its internal memory based on the observed effect its prediction had. Our meta-learner can be combined with any gradient-based optimizer, learns on the fly and can be transferred to new optimization tasks. In our evaluations we show that our meta-learning algorithm speeds up learning of MNIST classification and a variety of learning control tasks, either in batch or online learning settings.