A Tutorial on Meta-Reinforcement Learning
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
While deep reinforcement learning (RL) has fueled multiple high-profile successes in machine learning, it is held back from more widespread adoption by its often poor data efficiency and the limited generality of the policies it produces. A promising approach for alleviating these limitations is to cast the development of better RL algorithms as a machine learning problem itself in a process called meta-RL. Meta-RL is most commonly studied in a problem setting where, given a distribution of tasks, the goal is to learn a policy that is capable of adapting to any new task from the task distribution with as little data as possible. In this survey, we describe the meta-RL problem setting in detail as well as its major variations. We discuss how, at a high level, meta-RL research can be clustered based on the presence of a task distribution and the learning budget available for each individual task. Using these clusters, we then survey meta-RL algorithms and applications. We conclude by presenting the open problems on the path to making meta-RL part of the standard toolbox for a deep RL practitioner.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Continuous control with deep reinforcement learning
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1509.02971 · Cited by 10,782
Learning to Compare: Relation Network for Few-Shot Learning
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P. H. S., & Hospedales, T. M. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00131 · Cited by 5,816
Valiant, L. G. (1984) · Communications of the ACM · doi:10.1145/1968.1972 · Cited by 3,279
Generalizing from a Few Examples: A Survey on Few-shot Learning
Wang, Y., Yao, Q., Kwok, J. T., & Ni, L. M. (2021) · ACM Computing Surveys · doi:10.1145/3386252 · Cited by 3,165
THOMPSON, W. R. (1933) · Biometrika · doi:10.1093/biomet/25.3-4.285 · Cited by 2,712
The Arcade Learning Environment: An Evaluation Platform for General Agents
Bellemare, M. G., Naddaf, Y., Veness, J., & Bowling, M. (2013) · Journal of Artificial Intelligence Research · doi:10.1613/jair.3912 · Cited by 2,161
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Espeholt, L., Soyer, H., Munos, R., Simonyan, K., Mnih, V., Ward, T., Doron, Y., Firoiu, V., Harley, T., Dunning, I., et al. (2018) · arXiv · doi:10.48550/arxiv.1802.01561 · Cited by 1,708
Graves, A., Wayne, G., & Danihelka, I. (2014) · arXiv · doi:10.48550/arxiv.1410.5401 · Cited by 1,058
Meta-Learning in Neural Networks: A Survey
Hospedales, T., Antoniou, A., Micaelli, P., & Storkey, A. (2020) · arXiv · doi:10.48550/arxiv.2004.05439 · Cited by 886
Meta-Learning in Neural Networks: A Survey
Hospedales, T. M., Antoniou, A., Micaelli, P., & Storkey, A. J. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3079209 · Cited by 886
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Levine, S., Kumar, A., Tucker, G., & Fu, J. (2020) · arXiv · doi:10.48550/arxiv.2005.01643 · Cited by 824
Prefrontal cortex as a meta-reinforcement learning system
Wang, J. X., Kurth-Nelson, Z., Kumaran, D., Tirumala, D., Soyer, H., Leibo, J. Z., Hassabis, D., & Botvinick, M. (2018) · Nature Neuroscience · doi:10.1038/s41593-018-0147-8 · Cited by 596
A model of inductive bias learning
Baxter, J. (2000) · Journal of Artificial Intelligence Research · doi:10.1613/jair.731 · Cited by 582
Learning to Learn: Introduction and Overview
Thrun, S., & Pratt, L. (1998) · Learning to Learn · doi:10.1007/978-1-4615-5529-2_1 · Cited by 521
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
Yu, T., Quillen, D., He, Z., Julian, R., Narayan, A., Shively, H., Bellathur, A., Hausman, K., Finn, C., & Levine, S. (2019) · arXiv · doi:10.48550/arxiv.1910.10897 · Cited by 450
Self-citationAd Hoc Autonomous Agent Teams: Collaboration without Pre-Coordination
Stone, P., Kaminka, G., Kraus, S., & Rosenschein, J. (2010) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v24i1.7529 · Cited by 323
Preparing for the Unknown: Learning a Universal Policy with Online System Identification
Yu, W., Tan, J., Liu, C. K., & Turk, G. (2017) · arXiv · doi:10.48550/arxiv.1702.02453 · Cited by 237
Gotta Learn Fast: A New Benchmark for Generalization in RL
Nichol, A., Pfau, V., Hesse, C., Klimov, O., & Schulman, J. (2018) · arXiv · doi:10.48550/arxiv.1804.03720 · Cited by 204
A Survey of Zero-shot Generalisation in Deep Reinforcement Learning
Kirk, R., Zhang, A., Grefenstette, E., & Rocktäschel, T. (2023) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.14174 · Cited by 193
Gödel Machines: Fully Self-referential Optimal Universal Self-improvers
Schmidhuber, J. (2007) · Cognitive Technologies · doi:10.1007/978-3-540-68677-4_7 · Cited by 110
Meta Reinforcement Learning with Latent Variable Gaussian Processes
Sæmundsson, S., Hofmann, K., & Deisenroth, M. P. (2018) · arXiv · doi:10.48550/arxiv.1803.07551 · Cited by 106
Meta reinforcement learning for sim-to-real domain adaptation
Arndt, K., Hazara, M., Ghadirzadeh, A., & Kyrki, V. (2020) · 2020 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra40945.2020.9196540 · Cited by 97
The NetHack Learning Environment
Küttler, H., Nardelli, N., Miller, A. H., Raileanu, R., Selvatici, M., Grefenstette, E., & Rocktäschel, T. (2020) · arXiv · doi:10.48550/arxiv.2006.13760 · Cited by 44
Offline Meta-Reinforcement Learning with Online Self-Supervision
Pong, V. H., Nair, A., Smith, L., Huang, C., & Levine, S. (2021) · arXiv · doi:10.48550/arxiv.2107.03974 · Cited by 25
Transformers generalize differently from information stored in context vs in weights
Chan, S. C. Y., Dasgupta, I., Kim, J., Kumaran, D., Lampinen, A. K., & Hill, F. (2022) · arXiv · doi:10.48550/arxiv.2210.05675 · Cited by 11
Cited by
A Brief Overview of ChatGPT: The History, Status Quo and Potential Future Development
Wu, T., He, S., Liu, J., Sun, S., Liu, K., Han, Q.-L., & Tang, Y. (2023) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2023.123618 · Cited by 1,452
The Rise and Potential of Large Language Model Based Agents: A Survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.07864 · Cited by 972
The rise and potential of large language model based agents: a survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4222-0 · Cited by 970
Advances and Challenges in Meta-Learning: A Technical Review
Vettoruzzo, A., Bouguelia, M.-R., Vanschoren, J., Rögnvaldsson, T., & Santosh, K. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3357847 · Cited by 314
Harms from Increasingly Agentic Algorithmic Systems
Chan, A., Salganik, R., Markelius, A., Pang, C., Rajkumar, N., Krasheninnikov, D., Langosco, L., He, Z., Duan, Y., Carroll, M., et al. (2023) · 2023 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3593013.3594033 · Cited by 149
“In the current scientific paradigm of large-scale deep-learning, one instead provides high-level learning algorithms that tend to be task-agnostic or adapt to new tasks efficiently [Beck et al. 2023; Dong et al. 2022].”
Background
Metadata
- Authors
- Beck, J., Vuorio, R., Zheran Liu, E., Xiong, Z., Zintgraf, L., Finn, C., & Whiteson, S.
- Venue
- Foundations and Trends in Machine Learning
- Publisher
- Emerald
- Published
- 2025-04-03
- Volume
- 18
- Issue
- 2-3
- Pages
- 224-384
- ISSN
- 1935-8237 (ISSN-L)
- 1935-8245
- OpenAlex
- W4409116005
- Cited by
- 93
- References
- 26
- FWCI
- 24.97
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.