---
title: "Model-Agnostic Meta-Learning for Fast Adaptation of Deep"
description: "The paper proposes a way to train a neural network to quickly master a new task from just a few… 41 references, cited by 632 papers here."
authors: ["Chelsea Finn", "Pieter Abbeel", "Sergey Levine"]
year: 2017
venue: "arXiv:1703.03400"
source: "https://arxiv.org/abs/1703.03400"
doi: "10.48550/arxiv.1703.03400"
arxiv: "1703.03400"
licence: "arXiv — non-exclusive licence to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/finn-2017-model-agnostic-meta-learning-fast/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/finn-2017-model-agnostic-meta-learning-fast/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/) / Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

# Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

**Authors:** [Chelsea Finn](https://md.research.elamur.ai/free/en/authors/chelsea-finn/), [Pieter Abbeel](https://md.research.elamur.ai/free/en/authors/pieter-abbeel/) and [Sergey Levine](https://md.research.elamur.ai/free/en/authors/sergey-levine/) · **Year:** 2017 · **Venue:** arXiv:1703.03400 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1703.03400) · [PDF](https://arxiv.org/pdf/1703.03400) · [DOI 10.48550/arxiv.1703.03400](https://doi.org/10.48550/arxiv.1703.03400) · [arXiv 1703.03400](https://arxiv.org/abs/1703.03400) · [OpenAlex](https://openalex.org/W2604763608)

**Citations:** 5,917 citations (OpenAlex, 2026-10-14) · [632](https://md.research.elamur.ai/free/en/papers/finn-2017-model-agnostic-meta-learning-fast/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary

The paper proposes a way to train a neural network to quickly master a new task from just a few examples, i.e., in the few-shot regime. The authors present the MAML (Model-Agnostic Meta-Learning) algorithm. It is architecture-independent and suitable for any model trained with gradient descent. The model is given many related tasks and is trained not to solve each of them, but to find initial parameters θ from which one or a few gradient steps on a small sample yield good performance on a new task. In other words, MAML prepares a model that is easy to fine-tune. This requires neither new parameters nor a special architecture, such as a recurrent or Siamese network. One only needs to compute a "gradient of a gradient". The method was evaluated on three types of problems: regression, image classification, and reinforcement learning. On two few-shot classification benchmarks it achieved state-of-the-art results, and in RL it adapted considerably faster than standard pretraining. The paper is important because it offers a simple and universal foundation for meta-learning that can be applied to almost any model.

## Key points

- **Method**: the inner step adapts the parameters to a specific task (step α), while the outer step updates the shared initialization θ based on performance after adaptation (step β, SGD). The meta-gradient requires Hessian-vector products, so the authors also compare the method with a first-order approximation.
- **RL setup**: the policy is a network with two hidden layers of 100 units each and ReLU. The inner update uses REINFORCE, the meta-optimizer is TRPO, and Hessian-vector products are computed with finite differences.
- **2D Navigation**: the agent was meta-trained for a single policy gradient step from 20 trajectories. At test time it performed up to 4 updates of 40 samples each and, already after the first step, clearly outperformed pretraining and random initialization.
- **Locomotion in MuJoCo** (half-cheetah and 3D "ant"): the agent had to run at a target velocity (0–2 for cheetah, 0–3 for ant) or in a target direction. Horizon H = 200, 20 rollouts per step. MAML adapts within 2–3 steps, whereas pretraining is sometimes worse than even random initialization.
- **Publication**: Proceedings of ICML 2017 (PMLR 70), UC Berkeley and OpenAI. Videos of the policies are available at sites.google.com/view/maml.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of California, Berkeley](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) — University, Berkeley, United States · 209 works · 244,782 citations
- [OpenAI](https://md.research.elamur.ai/free/en/companies/openai/) — Company, San Francisco, United States · 23 works · 27,874 citations

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works

💡 Concepts (1): [💡 Few-shot learning](https://md.research.elamur.ai/free/en/concepts/few-shot-learning/) · 45 works

## Cite

Cite as: Chelsea Finn, Pieter Abbeel and Sergey Levine. 2017. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. arXiv:1703.03400.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{finn2017model,
  title = {{Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks}},
  author = {Chelsea Finn, Pieter Abbeel and Sergey Levine},
  year = {2017},
  doi = {10.48550/arxiv.1703.03400},
  eprint = {1703.03400},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1703.03400}
}
```

- [← previous Learning Transferable Architectures for Scalable Image Recognition](https://md.research.elamur.ai/free/en/papers/zoph-2017-learning-transferable-architectures-scalable-image/)
- [next → Explanation in Artificial Intelligence: Insights from the Social Sciences](https://md.research.elamur.ai/free/en/papers/miller-2017-explanation-artificial-intelligence-insights-social/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/)

## References

41 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abadi, Martı́n, Agarwal, Ashish, Barham, Paul, Brevdo, Eugene, Chen, Zhifeng, Citro, Craig, Corrado, Greg S, Davis, Andy, Dean, Jeffrey, Devin, Matthieu, et al. [Tensorflow: Large-scale machine learning on heterogeneous distributed systems](https://md.research.elamur.ai/free/en/papers/abadi-2016-tensorflow-large-scale-machine-learning/). arXiv preprint arXiv:1603.04467, 2016.
2. Andrychowicz, Marcin, Denil, Misha, Gomez, Sergio, Hoffman, Matthew W, Pfau, David, Schaul, Tom, and de Freitas, Nando. Learning to learn by gradient descent by gradient descent. In Neural Information Processing Systems (NIPS), 2016. [find](https://scholar.google.com/scholar?q=Andrychowicz%2C+Marcin%2C+Denil%2C+Misha%2C+Gomez%2C+Sergio%2C+Hoffman%2C+Matthew+W%2C+Pfau%2C+David%2C+Schaul%2C+Tom%2C+and+de+Freitas%2C+Nando%2E+Learning+to+learn+by+gradient+descent+by+gradient+descent%2E+In+Neural+Information)
3. Bengio, Samy, Bengio, Yoshua, Cloutier, Jocelyn, and Gecsei, Jan. On the optimization of a synaptic learning rule. In Optimality in Artificial and Biological Neural Networks, pp. 6–8, 1992. [find](https://scholar.google.com/scholar?q=Bengio%2C+Samy%2C+Bengio%2C+Yoshua%2C+Cloutier%2C+Jocelyn%2C+and+Gecsei%2C+Jan%2E+On+the+optimization+of+a+synaptic+learning+rule%2E+In+Optimality+in+Artificial+and+Biological+Neural+Networks%2C+pp%2E+6%E2%80%938%2C+1992%2E)
4. Bengio, Yoshua, Bengio, Samy, and Cloutier, Jocelyn. Learning a synaptic learning rule. Université de Montréal, Département d’informatique et de recherche opérationnelle, 1990. [find](https://scholar.google.com/scholar?q=Bengio%2C+Yoshua%2C+Bengio%2C+Samy%2C+and+Cloutier%2C+Jocelyn%2E+Learning+a+synaptic+learning+rule%2E+Universite%CC%81+de+Montre%CC%81al%2C+De%CC%81partement+d%E2%80%99informatique+et+de+recherche+ope%CC%81rationnelle%2C+1990%2E)
5. Donahue, Jeff, Jia, Yangqing, Vinyals, Oriol, Hoffman, Judy, Zhang, Ning, Tzeng, Eric, and Darrell, Trevor. [Decaf: A deep convolutional activation feature for generic visual recognition](https://md.research.elamur.ai/free/en/papers/donahue-2013-decaf-deep-convolutional-activation-feature/). In International Conference on Machine Learning (ICML), 2014.
6. Duan, Yan, Chen, Xi, Houthooft, Rein, Schulman, John, and Abbeel, Pieter. Benchmarking deep reinforcement learning for continuous control. In International Conference on Machine Learning (ICML), 2016a. [find](https://scholar.google.com/scholar?q=Duan%2C+Yan%2C+Chen%2C+Xi%2C+Houthooft%2C+Rein%2C+Schulman%2C+John%2C+and+Abbeel%2C+Pieter%2E+Benchmarking+deep+reinforcement+learning+for+continuous+control%2E+In+International+Conference+on+Machine+Learning+%28ICML%29%2C+2016a)
7. Duan, Yan, Schulman, John, Chen, Xi, Bartlett, Peter L, Sutskever, Ilya, and Abbeel, Pieter. Rl2: Fast reinforcement learning via slow reinforcement learning. arXiv preprint arXiv:1611.[02779, 2016b](https://md.research.elamur.ai/free/en/papers/duan-2016-rl-2-fast-reinforcement-learning/).
8. Edwards, Harrison and Storkey, Amos. Towards a neural statistician. International Conference on Learning Representations (ICLR), 2017. [find](https://scholar.google.com/scholar?q=Edwards%2C+Harrison+and+Storkey%2C+Amos%2E+Towards+a+neural+statistician%2E+International+Conference+on+Learning+Representations+%28ICLR%29%2C+2017%2E)
9. Goodfellow, Ian J, Shlens, Jonathon, and Szegedy, Christian. [Explaining and harnessing adversarial examples](https://md.research.elamur.ai/free/en/papers/goodfellow-2014-explaining-harnessing-adversarial-examples/). International Conference on Learning Representations (ICLR), 2015.
10. Ha, David, Dai, Andrew, and Le, Quoc V. Hypernetworks. International Conference on Learning Representations (ICLR), 2017. [find](https://scholar.google.com/scholar?q=Ha%2C+David%2C+Dai%2C+Andrew%2C+and+Le%2C+Quoc+V%2E+Hypernetworks%2E+International+Conference+on+Learning+Representations+%28ICLR%29%2C+2017%2E)
11. Hochreiter, Sepp, Younger, A Steven, and Conwell, Peter R. Learning to learn using gradient descent. In International Conference on Artificial Neural Networks. Springer, 2001. [find](https://scholar.google.com/scholar?q=Hochreiter%2C+Sepp%2C+Younger%2C+A+Steven%2C+and+Conwell%2C+Peter+R%2E+Learning+to+learn+using+gradient+descent%2E+In+International+Conference+on+Artificial+Neural+Networks%2E+Springer%2C+2001%2E)
12. Husken, Michael and Goerick, Christian. Fast learning for problem classes using knowledge based network initialization. In Neural Networks, 2000. [find](https://scholar.google.com/scholar?q=Husken%2C+Michael+and+Goerick%2C+Christian%2E+Fast+learning+for+problem+classes+using+knowledge+based+network+initialization%2E+In+Neural+Networks%2C+2000%2E)
13. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on, volume 6, pp. 619–624. [find](https://scholar.google.com/scholar?q=IJCNN+2000%2C+Proceedings+of+the+IEEE%2DINNS%2DENNS+International+Joint+Conference+on%2C+volume+6%2C+pp%2E+619%E2%80%93624%2E)
14. Ioffe, Sergey and Szegedy, Christian. Batch normalization: Accelerating deep network training by reducing internal covariate shift. International Conference on Machine Learning (ICML), 2015. [find](https://scholar.google.com/scholar?q=Ioffe%2C+Sergey+and+Szegedy%2C+Christian%2E+Batch+normalization%3A+Accelerating+deep+network+training+by+reducing+internal+covariate+shift%2E+International+Conference+on+Machine+Learning+%28ICML%29%2C+2015%2E)
15. Kaiser, Lukasz, Nachum, Ofir, Roy, Aurko, and Bengio, Samy. Learning to remember rare events. International Conference on Learning Representations (ICLR), 2017. [find](https://scholar.google.com/scholar?q=Kaiser%2C+Lukasz%2C+Nachum%2C+Ofir%2C+Roy%2C+Aurko%2C+and+Bengio%2C+Samy%2E+Learning+to+remember+rare+events%2E+International+Conference+on+Learning+Representations+%28ICLR%29%2C+2017%2E)
16. Kingma, Diederik and Ba, Jimmy. [Adam: A method for stochastic optimization](https://md.research.elamur.ai/free/en/papers/kingma-2014-adam-method-stochastic-optimization/). International Conference on Learning Representations (ICLR), 2015.
17. Kirkpatrick, James, Pascanu, Razvan, Rabinowitz, Neil, Veness, Joel, Desjardins, Guillaume, Rusu, Andrei A, Milan, Kieran, Quan, John, Ramalho, Tiago, Grabska-Barwinska, Agnieszka, et al. Overcoming catastrophic forgetting in neural networks. arXiv preprint arXiv:1612.00796, 2016. [find](https://scholar.google.com/scholar?q=Kirkpatrick%2C+James%2C+Pascanu%2C+Razvan%2C+Rabinowitz%2C+Neil%2C+Veness%2C+Joel%2C+Desjardins%2C+Guillaume%2C+Rusu%2C+Andrei+A%2C+Milan%2C+Kieran%2C+Quan%2C+John%2C+Ramalho%2C+Tiago%2C+Grabska%2DBarwinska%2C+Agnieszka%2C+et+al%2E+Overcoming+c)
18. Koch, Gregory. Siamese neural networks for one-shot image recognition. ICML Deep Learning Workshop, 2015. [find](https://scholar.google.com/scholar?q=Koch%2C+Gregory%2E+Siamese+neural+networks+for+one%2Dshot+image+recognition%2E+ICML+Deep+Learning+Workshop%2C+2015%2E)
19. Krähenbühl, Philipp, Doersch, Carl, Donahue, Jeff, and Darrell, Trevor. Data-dependent initializations of convolutional neural networks. International Conference on Learning Representations (ICLR), 2016. [find](https://scholar.google.com/scholar?q=Kra%CC%88henbu%CC%88hl%2C+Philipp%2C+Doersch%2C+Carl%2C+Donahue%2C+Jeff%2C+and+Darrell%2C+Trevor%2E+Data%2Ddependent+initializations+of+convolutional+neural+networks%2E+International+Conference+on+Learning+Representations+%28ICLR%29%2C+)
20. Lake, Brenden M, Salakhutdinov, Ruslan, Gross, Jason, and Tenenbaum, Joshua B. One shot learning of simple visual concepts. In Conference of the Cognitive Science Society (CogSci), 2011. [find](https://scholar.google.com/scholar?q=Lake%2C+Brenden+M%2C+Salakhutdinov%2C+Ruslan%2C+Gross%2C+Jason%2C+and+Tenenbaum%2C+Joshua+B%2E+One+shot+learning+of+simple+visual+concepts%2E+In+Conference+of+the+Cognitive+Science+Society+%28CogSci%29%2C+2011%2E)
21. Li, Ke and Malik, Jitendra. Learning to optimize. International Conference on Learning Representations (ICLR), 2017. [find](https://scholar.google.com/scholar?q=Li%2C+Ke+and+Malik%2C+Jitendra%2E+Learning+to+optimize%2E+International+Conference+on+Learning+Representations+%28ICLR%29%2C+2017%2E)
22. Maclaurin, Dougal, Duvenaud, David, and Adams, Ryan. Gradient-based hyperparameter optimization through reversible learning. In International Conference on Machine Learning (ICML), 2015. [find](https://scholar.google.com/scholar?q=Maclaurin%2C+Dougal%2C+Duvenaud%2C+David%2C+and+Adams%2C+Ryan%2E+Gradient%2Dbased+hyperparameter+optimization+through+reversible+learning%2E+In+International+Conference+on+Machine+Learning+%28ICML%29%2C+2015%2E)
23. Munkhdalai, Tsendsuren and Yu, Hong. Meta networks. International Conferecence on Machine Learning (ICML), 2017. [find](https://scholar.google.com/scholar?q=Munkhdalai%2C+Tsendsuren+and+Yu%2C+Hong%2E+Meta+networks%2E+International+Conferecence+on+Machine+Learning+%28ICML%29%2C+2017%2E)
24. Naik, Devang K and Mammone, RJ. Meta-neural networks that learn by learning. In International Joint Conference on Neural Netowrks (IJCNN), 1992. [find](https://scholar.google.com/scholar?q=Naik%2C+Devang+K+and+Mammone%2C+RJ%2E+Meta%2Dneural+networks+that+learn+by+learning%2E+In+International+Joint+Conference+on+Neural+Netowrks+%28IJCNN%29%2C+1992%2E)
25. Parisotto, Emilio, Ba, Jimmy Lei, and Salakhutdinov, Ruslan. Actor-mimic: Deep multitask and transfer reinforcement learning. International Conference on Learning Representations (ICLR), 2016. [find](https://scholar.google.com/scholar?q=Parisotto%2C+Emilio%2C+Ba%2C+Jimmy+Lei%2C+and+Salakhutdinov%2C+Ruslan%2E+Actor%2Dmimic%3A+Deep+multitask+and+transfer+reinforcement+learning%2E+International+Conference+on+Learning+Representations+%28ICLR%29%2C+2016%2E)
26. Ravi, Sachin and Larochelle, Hugo. Optimization as a model for few-shot learning. In International Conference on Learning Representations (ICLR), 2017. [find](https://scholar.google.com/scholar?q=Ravi%2C+Sachin+and+Larochelle%2C+Hugo%2E+Optimization+as+a+model+for+few%2Dshot+learning%2E+In+International+Conference+on+Learning+Representations+%28ICLR%29%2C+2017%2E)
27. Rei, Marek. Online representation learning in recurrent neural language models. arXiv preprint arXiv:1508.03854, 2015. [find](https://scholar.google.com/scholar?q=Rei%2C+Marek%2E+Online+representation+learning+in+recurrent+neural+language+models%2E+arXiv+preprint+arXiv%3A1508%2E03854%2C+2015%2E)
28. Rezende, Danilo Jimenez, Mohamed, Shakir, Danihelka, Ivo, Gregor, Karol, and Wierstra, Daan. One-shot generalization in deep generative models. International Conference on Machine Learning (ICML), 2016. [find](https://scholar.google.com/scholar?q=Rezende%2C+Danilo+Jimenez%2C+Mohamed%2C+Shakir%2C+Danihelka%2C+Ivo%2C+Gregor%2C+Karol%2C+and+Wierstra%2C+Daan%2E+One%2Dshot+generalization+in+deep+generative+models%2E+International+Conference+on+Machine+Learning+%28ICML%29%2C+201)
29. Salimans, Tim and Kingma, Diederik P. Weight normalization: A simple reparameterization to accelerate training of deep neural networks. In Neural Information Processing Systems (NIPS), 2016. [find](https://scholar.google.com/scholar?q=Salimans%2C+Tim+and+Kingma%2C+Diederik+P%2E+Weight+normalization%3A+A+simple+reparameterization+to+accelerate+training+of+deep+neural+networks%2E+In+Neural+Information+Processing+Systems+%28NIPS%29%2C+2016%2E)
30. Santoro, Adam, Bartunov, Sergey, Botvinick, Matthew, Wierstra, Daan, and Lillicrap, Timothy. Meta-learning with memory-augmented neural networks. In International Conference on Machine Learning (ICML), 2016. [find](https://scholar.google.com/scholar?q=Santoro%2C+Adam%2C+Bartunov%2C+Sergey%2C+Botvinick%2C+Matthew%2C+Wierstra%2C+Daan%2C+and+Lillicrap%2C+Timothy%2E+Meta%2Dlearning+with+memory%2Daugmented+neural+networks%2E+In+International+Conference+on+Machine+Learning+%28ICML%29)
31. Saxe, Andrew, McClelland, James, and Ganguli, Surya. [Exact solutions to the nonlinear dynamics of learning in deep linear neural networks](https://md.research.elamur.ai/free/en/papers/saxe-2013-exact-solutions-nonlinear-dynamics-learning/). International Conference on Learning Representations (ICLR), 2014.
32. Schmidhuber, Jurgen. Evolutionary principles in self-referential learning. On learning how to learn: The meta-meta-... hook.) Diploma thesis, Institut f. Informatik, Tech. Univ. Munich, 1987. [find](https://scholar.google.com/scholar?q=Schmidhuber%2C+Jurgen%2E+Evolutionary+principles+in+self%2Dreferential+learning%2E+On+learning+how+to+learn%3A+The+meta%2Dmeta%2D%2E%2E%2E+hook%2E%29+Diploma+thesis%2C+Institut+f%2E+Informatik%2C+Tech%2E+Univ%2E+Munich%2C+1987%2E)
33. Schmidhuber, Jürgen. Learning to control fast-weight memories: An alternative to dynamic recurrent networks. Neural Computation, 1992. [find](https://scholar.google.com/scholar?q=Schmidhuber%2C+Ju%CC%88rgen%2E+Learning+to+control+fast%2Dweight+memories%3A+An+alternative+to+dynamic+recurrent+networks%2E+Neural+Computation%2C+1992%2E)
34. Schulman, John, Levine, Sergey, Abbeel, Pieter, Jordan, Michael I, and Moritz, Philipp. Trust region policy optimization. In International Conference on Machine Learning (ICML), 2015. [find](https://scholar.google.com/scholar?q=Schulman%2C+John%2C+Levine%2C+Sergey%2C+Abbeel%2C+Pieter%2C+Jordan%2C+Michael+I%2C+and+Moritz%2C+Philipp%2E+Trust+region+policy+optimization%2E+In+International+Conference+on+Machine+Learning+%28ICML%29%2C+2015%2E)
35. Shyam, Pranav, Gupta, Shubham, and Dukkipati, Ambedkar. Attentive recurrent comparators. International Conferecence on Machine Learning (ICML), 2017. [find](https://scholar.google.com/scholar?q=Shyam%2C+Pranav%2C+Gupta%2C+Shubham%2C+and+Dukkipati%2C+Ambedkar%2E+Attentive+recurrent+comparators%2E+International+Conferecence+on+Machine+Learning+%28ICML%29%2C+2017%2E)
36. Snell, Jake, Swersky, Kevin, and Zemel, Richard S. Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175, 2017. [find](https://scholar.google.com/scholar?q=Snell%2C+Jake%2C+Swersky%2C+Kevin%2C+and+Zemel%2C+Richard+S%2E+Prototypical+networks+for+few%2Dshot+learning%2E+arXiv+preprint+arXiv%3A1703%2E05175%2C+2017%2E)
37. Thrun, Sebastian and Pratt, Lorien. Learning to learn. Springer Science & Business Media, 1998. [find](https://scholar.google.com/scholar?q=Thrun%2C+Sebastian+and+Pratt%2C+Lorien%2E+Learning+to+learn%2E+Springer+Science+%26+Business+Media%2C+1998%2E)
38. Todorov, Emanuel, Erez, Tom, and Tassa, Yuval. Mujoco: A physics engine for model-based control. In International Conference on Intelligent Robots and Systems (IROS), 2012. [find](https://scholar.google.com/scholar?q=Todorov%2C+Emanuel%2C+Erez%2C+Tom%2C+and+Tassa%2C+Yuval%2E+Mujoco%3A+A+physics+engine+for+model%2Dbased+control%2E+In+International+Conference+on+Intelligent+Robots+and+Systems+%28IROS%29%2C+2012%2E)
39. Vinyals, Oriol, Blundell, Charles, Lillicrap, Tim, Wierstra, Daan, et al. [Matching networks for one shot learning](https://md.research.elamur.ai/free/en/papers/vinyals-2016-matching-networks-one-shot-learning/). In Neural Information Processing Systems (NIPS), 2016.
40. Wang, Jane X, Kurth-Nelson, Zeb, Tirumala, Dhruva, Soyer, Hubert, Leibo, Joel Z, Munos, Remi, Blundell, Charles, Kumaran, Dharshan, and Botvinick, Matt. Learning to reinforcement learn. arXiv preprint arXiv:1611.05763, 2016. — [arXiv:1611.05763](https://arxiv.org/abs/1611.05763) [find](https://scholar.google.com/scholar?q=Wang%2C+Jane+X%2C+Kurth%2DNelson%2C+Zeb%2C+Tirumala%2C+Dhruva%2C+Soyer%2C+Hubert%2C+Leibo%2C+Joel+Z%2C+Munos%2C+Remi%2C+Blundell%2C+Charles%2C+Kumaran%2C+Dharshan%2C+and+Botvinick%2C+Matt%2E+Learning+to+reinforcement+learn%2E+arXiv+preprint)
41. Williams, Ronald J. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, 8(3-4):229–256, 1992. [find](https://scholar.google.com/scholar?q=Williams%2C+Ronald+J%2E+Simple+statistical+gradient%2Dfollowing+algorithms+for+connectionist+reinforcement+learning%2E+Machine+learning%2C+8%283%2D4%29%3A229%E2%80%93256%2C+1992%2E)

*Updated 2 November 2026*