https://github.com/Alro10/meta-learning-resources

A curated list of meta-learning resources: papers, coding, tutorials, etc.
https://github.com/Alro10/meta-learning-resources

deep-reinforcement-learning meta-learning reinforcement-learning

Last synced: 18 days ago
JSON representation

A curated list of meta-learning resources: papers, coding, tutorials, etc.

• Host: GitHub
• URL: https://github.com/Alro10/meta-learning-resources
• Owner: Alro10
• License: apache-2.0
• Created: 2019-05-15T02:01:13.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2019-12-02T12:55:28.000Z (about 6 years ago)
• Last Synced: 2025-03-13T18:12:44.079Z (9 months ago)
• Topics: deep-reinforcement-learning, meta-learning, reinforcement-learning
• Homepage:
• Size: 130 KB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-automl -

README

          
# Meta-Learning Resources

A curated list of meta-learning papers, code, tutorials, etc.

Under developing!







*Figure by BAIR Lab*

## [Table of Contents]()

* [Papers](#Papers)

* [Tutorials](#Tutorials)

* [Code](#Resources)

## Papers

### 2019

- [Meta-Learning of Neural Architectures for Few-Shot Learning](https://arxiv.org/pdf/1911.11090.pdf)

  - Thomas Elsken, et al.

  - not yet

- [Meta-Q-Learning](https://arxiv.org/pdf/1910.00125.pdf)

  - Code-not yet

  - Rasool Fakoor, et al.

- [Meta-Learning with Implicit Gradients](https://arxiv.org/pdf/1909.04630.pdf) **NeurIPS 2019. First two authors contributed equally**

  - Aravind Rajeswaran, Chelsea Finn, Sham Kakade, Sergey Levine. 

  - Code- not yet

- [Metalearned Neural Memory](https://arxiv.org/abs/1907.09720).

  - Tsendsuren Munkhdalai, Alessandro Sordoni, Tong Wang, Adam Trischler.

  - Code- not yet

- [Meta-Transfer Learning for Few-Shot Learning](https://arxiv.org/abs/1812.02391). **CVPR 2019**

  - Qianru Sun, Yaoyao Liu, Tat-Seng Chua, Bernt Schiele.

  - [[Code-TensorFlow](https://github.com/y2l/meta-transfer-learning-tensorflow)]

  - [[Code-Pytorch](git@github.com:Alro10/meta-learning-resources.git)]

- [Meta-learning with differentiable closed-form solvers](https://arxiv.org/abs/1805.08136). **ICLR 2019**

  - Luca Bertinetto, João F. Henriques, Philip H.S. Torr, Andrea Vedaldi.

  - [[Code](https://github.com/bertinetto/r2d2)]

- [Meta reinforcement learning as task inference](https://arxiv.org/abs/1905.06424). **DeepMind**

  - Jan Humplik, Alexandre Galashov, LeonardDeepMind Hasenclever, Pedro A. Ortega, Yee Whye Teh, Nicolas Heess.

### 2018

- [Meta-Reinforcement Learning of Structured Exploration Strategies](https://papers.nips.cc/paper/7776-meta-reinforcement-learning-of-structured-exploration-strategies.pdf). **NeurIPS 2018**

  - Abhishek Gupta, Russell Mendonca, YuXuan Liu, Pieter Abbeel, Sergey Levine.

### 2017

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://arxiv.org/abs/1703.03400). **ICML 2017**

  - Chelsea Finn, Pieter Abbeel, Sergey Levine.

  - [[Code](https://github.com/cbfinn/maml)]

## Code

- [TensorFlow 2.0 implementation of MAML](https://github.com/mari-linhares/tensorflow-maml)  by Marianne Linhares.