Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Human-level control through deep reinforcement learning
201517.2k citationsVolodymyr Mnih, Koray Kavukcuoglu et al.Natureprofile →
This map shows the geographic impact of Daan Wierstra's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Daan Wierstra with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Daan Wierstra more than expected).
This network shows the impact of papers produced by Daan Wierstra. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Daan Wierstra. The network helps show where Daan Wierstra may publish in the future.
Co-authorship network of co-authors of Daan Wierstra
This figure shows the co-authorship network connecting the top 25 collaborators of Daan Wierstra.
A scholar is included among the top collaborators of Daan Wierstra based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Daan Wierstra. Daan Wierstra is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Mott, A., Daniel Zoran, Mike Chrzanowski, Daan Wierstra, & Danilo Jimenez Rezende. (2018). S3TA: A Soft, Spatial, Sequential, Top-Down Attention Model.1 indexed citations
2.
Racanière, Sébastien, Théophane Weber, David Reichert, et al.. (2017). Imagination-Augmented Agents for Deep Reinforcement Learning. arXiv (Cornell University). 30. 5690–5701.49 indexed citations
3.
Chiappa, Silvia, Sébastien Racanière, Daan Wierstra, & Shakir Mohamed. (2017). Recurrent Environment Simulators. International Conference on Learning Representations.9 indexed citations
Mnih, Volodymyr, Koray Kavukcuoglu, David Silver, et al.. (2015). Human-level control through deep reinforcement learning. Nature. 518(7540). 529–533.17153 indexed citations breakdown →
13.
Rezende, Danilo Jimenez, Shakir Mohamed, & Daan Wierstra. (2014). Stochastic Back-propagation and Variational Inference in Deep Latent Gaussian Models.. arXiv (Cornell University).30 indexed citations
Sun, Yi, et al.. (2009). Efficient Natural Evolution Strategies Evolution Strategies and Evolutionary Programming Track.1 indexed citations
16.
Wierstra, Daan, et al.. (2008). Natural Evolution Strategies.152 indexed citations
17.
Wierstra, Daan, et al.. (2008). Natural Evolution Strategies. Journal of Machine Learning Research. 15(1). 3381–3387.126 indexed citations
18.
Schmidhuber, Jürgen, Daan Wierstra, & Faustino Gomez. (2005). Evolino: hybrid neuroevolution / optimal linear search for sequence learning. International Joint Conference on Artificial Intelligence. 853–858.56 indexed citations
19.
Wierstra, Daan, et al.. (2005). Evolino: Hybrid Neuroevolution / Optimal Linear Search for Sequence Prediction. mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich).18 indexed citations
20.
Wierstra, Daan & Marco Wiering. (2004). Utile distinction hidden Markov models. mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich). 108–108.14 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.