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.
Computer Science Curricula 2023
202459 citationsEric Eaton, Susan L. Epstein et al.profile →
Peers — A (Enhanced Table)
Peers by citation overlap · career bar shows stage (early→late)
cites ·
hero ref
This map shows the geographic impact of Eric Eaton'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 Eric Eaton with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Eric Eaton more than expected).
This network shows the impact of papers produced by Eric Eaton. 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 Eric Eaton. The network helps show where Eric Eaton may publish in the future.
Co-authorship network of co-authors of Eric Eaton
This figure shows the co-authorship network connecting the top 25 collaborators of Eric Eaton.
A scholar is included among the top collaborators of Eric Eaton 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 Eric Eaton. Eric Eaton is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Eaton, Eric. (2022). Insectpedia. Princeton University Press eBooks.1 indexed citations
8.
Wang, Boyu, et al.. (2020). Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting. arXiv (Cornell University). 33. 14398–14409.1 indexed citations
Wang, Boyu, et al.. (2019). Transfer Learning via Minimizing the Performance Gap Between Domains. Neural Information Processing Systems. 32. 10644–10654.18 indexed citations
Ammar, Haitham Bou, Eric Eaton, José Marcio Luna, & Paul Ruvolo. (2015). Autonomous cross-domain knowledge transfer in lifelong policy gradient reinforcement learning. International Conference on Artificial Intelligence. 3345–3351.30 indexed citations
14.
Ammar, Haitham Bou, Eric Eaton, Matthew E. Taylor, et al.. (2014). An automated measure of MDP similarity for transfer in reinforcement learning. National Conference on Artificial Intelligence. 31–37.29 indexed citations
15.
Ammar, Haitham Bou, Eric Eaton, Paul Ruvolo, & Matthew E. Taylor. (2014). Online Multi-Task Learning for Policy Gradient Methods. International Conference on Machine Learning. 1206–1214.74 indexed citations
16.
Ruvolo, Paul & Eric Eaton. (2013). ELLA: An Efficient Lifelong Learning Algorithm. International Conference on Machine Learning. 507–515.144 indexed citations
17.
Ruvolo, Paul & Eric Eaton. (2013). Scalable Lifelong Learning with Active Task Selection. National Conference on Artificial Intelligence.7 indexed citations
18.
Eaton, Eric, et al.. (2007). Using multiresolution learning for transfer in image classification. National Conference on Artificial Intelligence. 1852–1853.2 indexed citations
19.
Eaton, Eric. (2006). Multi-resolution learning for knowledge transfer. National Conference on Artificial Intelligence. 1908–1909.2 indexed citations
20.
Eaton, Eric & Kiri L. Wagstaff. (2005). A context-sensitive and user-centric approach to developing personal assistants. National Conference on Artificial Intelligence. 98–100.1 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.