Meta Reinforcement Learning with Latent Variable Gaussian Processes

Steindor Saemundsson, Katja Hofmann, Marc Peter Deisenroth
Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, PMLR R16:641-651, 2018.

Abstract

Learning from small data sets is critical in many practical applications where data collection is time consuming or expensive, e.g., robotics, animal experiments or drug design. Meta learning is one way to increase the data efficiency of learning algorithms by generalizing learned concepts from a set of training tasks to unseen, but related, tasks. Often, this relationship between tasks is hard coded or relies in some other way on human expertise. In this paper, we frame meta learning as a hierarchical latent variable model and infer the relationship between tasks automatically from data. We apply our framework in a model-based reinforcement learning setting and show that our meta-learning model effectively generalizes to novel tasks by identifying how new tasks relate to prior ones from minimal data. This results in up to a 60% reduction in the average interaction time needed to solve tasks compared to strong baselines.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR16-saemundsson18a, title = {Meta Reinforcement Learning with Latent Variable {G}aussian Processes}, author = {Saemundsson, Steindor and Hofmann, Katja and Deisenroth, Marc Peter}, booktitle = {Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence}, pages = {641--651}, year = {2018}, editor = {Globerson, Amir and Silva, Ricardo}, volume = {R16}, series = {Proceedings of Machine Learning Research}, month = {06--10 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r16/main/assets/saemundsson18a/saemundsson18a.pdf}, url = {https://proceedings.mlr.press/r16/saemundsson18a.html}, abstract = {Learning from small data sets is critical in many practical applications where data collection is time consuming or expensive, e.g., robotics, animal experiments or drug design. Meta learning is one way to increase the data efficiency of learning algorithms by generalizing learned concepts from a set of training tasks to unseen, but related, tasks. Often, this relationship between tasks is hard coded or relies in some other way on human expertise. In this paper, we frame meta learning as a hierarchical latent variable model and infer the relationship between tasks automatically from data. We apply our framework in a model-based reinforcement learning setting and show that our meta-learning model effectively generalizes to novel tasks by identifying how new tasks relate to prior ones from minimal data. This results in up to a 60% reduction in the average interaction time needed to solve tasks compared to strong baselines.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Meta Reinforcement Learning with Latent Variable Gaussian Processes %A Steindor Saemundsson %A Katja Hofmann %A Marc Peter Deisenroth %B Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2018 %E Amir Globerson %E Ricardo Silva %F pmlr-vR16-saemundsson18a %I PMLR %P 641--651 %U https://proceedings.mlr.press/r16/saemundsson18a.html %V R16 %X Learning from small data sets is critical in many practical applications where data collection is time consuming or expensive, e.g., robotics, animal experiments or drug design. Meta learning is one way to increase the data efficiency of learning algorithms by generalizing learned concepts from a set of training tasks to unseen, but related, tasks. Often, this relationship between tasks is hard coded or relies in some other way on human expertise. In this paper, we frame meta learning as a hierarchical latent variable model and infer the relationship between tasks automatically from data. We apply our framework in a model-based reinforcement learning setting and show that our meta-learning model effectively generalizes to novel tasks by identifying how new tasks relate to prior ones from minimal data. This results in up to a 60% reduction in the average interaction time needed to solve tasks compared to strong baselines. %Z Reissued by PMLR on 04 October 2026.
APA
Saemundsson, S., Hofmann, K. & Deisenroth, M.P.. (2018). Meta Reinforcement Learning with Latent Variable Gaussian Processes. Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R16:641-651 Available from https://proceedings.mlr.press/r16/saemundsson18a.html. Reissued by PMLR on 04 October 2026.

Related Material