Philip S. Thomas

1.9k total citations
45 papers, 790 citations indexed

About

Philip S. Thomas is a scholar working on Artificial Intelligence, Management Science and Operations Research and Cognitive Neuroscience. According to data from OpenAlex, Philip S. Thomas has authored 45 papers receiving a total of 790 indexed citations (citations by other indexed papers that have themselves been cited), including 25 papers in Artificial Intelligence, 13 papers in Management Science and Operations Research and 5 papers in Cognitive Neuroscience. Recurrent topics in Philip S. Thomas's work include Reinforcement Learning in Robotics (16 papers), Advanced Bandit Algorithms Research (11 papers) and Evolutionary Algorithms and Applications (6 papers). Philip S. Thomas is often cited by papers focused on Reinforcement Learning in Robotics (16 papers), Advanced Bandit Algorithms Research (11 papers) and Evolutionary Algorithms and Applications (6 papers). Philip S. Thomas collaborates with scholars based in United States, Brazil and Canada. Philip S. Thomas's co-authors include Georgios Theocharous, Mohammad Ghavamzadeh, George Konidaris, Sarah Osentoski, Andrew G. Barto, Emma Brunskill, Kathleen M. Jagodnik, Michael S. Branicky, Antonie J. van den Bogert and Stephen Giguere and has published in prestigious journals such as Science, Long Range Planning and IEEE Transactions on Neural Systems and Rehabilitation Engineering.

In The Last Decade

Philip S. Thomas

43 papers receiving 709 citations

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Philip S. Thomas United States	14	406	137	93	79	79	45	790
Shahnorbanun Sahran Malaysia	17	366 0.9×	25 0.2×	45 0.5×	56 0.7×	63 0.8×	88	1.0k
Jing Xiao China	15	400 1.0×	370 2.7×	72 0.8×	28 0.4×	91 1.2×	41	865
Bijan Raahemi Canada	17	500 1.2×	136 1.0×	37 0.4×	35 0.4×	28 0.4×	69	995
Kangping Wang China	13	512 1.3×	53 0.4×	88 0.9×	23 0.3×	103 1.3×	42	1.1k
Hojjat Adeli United States	12	140 0.3×	96 0.7×	63 0.7×	33 0.4×	33 0.4×	30	645
Mihaela Ulieru Canada	17	224 0.6×	109 0.8×	174 1.9×	79 1.0×	38 0.5×	84	864
Lidia Ogiela Poland	21	624 1.5×	31 0.2×	56 0.6×	49 0.6×	87 1.1×	103	1.0k
Hussain AlSalman Saudi Arabia	21	332 0.8×	124 0.9×	50 0.5×	18 0.2×	51 0.6×	62	1.1k
James N.K. Liu Hong Kong	12	232 0.6×	121 0.9×	73 0.8×	30 0.4×	51 0.6×	28	774
Jesús Cerquides Spain	17	404 1.0×	224 1.6×	45 0.5×	29 0.4×	78 1.0×	86	940

Countries citing papers authored by Philip S. Thomas

Since Specialization

Citations

This map shows the geographic impact of Philip S. Thomas'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 Philip S. Thomas with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Philip S. Thomas more than expected).

Fields of papers citing papers by Philip S. Thomas

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Philip S. Thomas. 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 Philip S. Thomas. The network helps show where Philip S. Thomas may publish in the future.

Co-authorship network of co-authors of Philip S. Thomas

This figure shows the co-authorship network connecting the top 25 collaborators of Philip S. Thomas. A scholar is included among the top collaborators of Philip S. Thomas 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 Philip S. Thomas. Philip S. Thomas is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

Hoag, Austin, et al.. (2024). Analyzing the Relationship Between Difference and Ratio-Based Fairness Metrics. 518–528.

Kaye, S., et al.. (2023). Isotope dependence of transport in ST40 hot ion mode plasmas. Plasma Physics and Controlled Fusion. 65(9). 95012–95012. 3 indexed citations

Allan, James, et al.. (2021). Large-scale Interactive Conversational Recommendation System using Actor-Critic Framework. 220–229. 5 indexed citations

Thomas, Philip S., et al.. (2020). Is the Policy Gradient a Gradient?. arXiv (Cornell University). 939–947. 2 indexed citations

Özışık, Pınar & Philip S. Thomas. (2020). Security Analysis of Safe and Seldonian Reinforcement Learning Algorithms. Neural Information Processing Systems. 33. 8959–8970. 2 indexed citations

Thomas, Philip S., et al.. (2019). A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning. Adaptive Agents and Multi-Agents Systems. 32. 1976–1978. 3 indexed citations

Silva, Bruno C. da, et al.. (2019). A Compression-Inspired Framework for Macro Discovery. arXiv (Cornell University). 1973–1975. 1 indexed citations

Thomas, Philip S. & Erik Learned-Miller. (2019). Concentration Inequalities for Conditional Value at Risk. International Conference on Machine Learning. 6225–6233. 6 indexed citations

Giguere, Stephen, et al.. (2019). Offline Contextual Bandits with High Probability Fairness Guarantees. Neural Information Processing Systems. 32. 14893–14904. 13 indexed citations

10.

Hanna, Josiah P., Philip S. Thomas, Peter Stone, & Scott Niekum. (2017). Data-Efficient Policy Evaluation Through Behavior Policy Search. International Conference on Machine Learning. 1394–1403. 2 indexed citations

11.

Thomas, Philip S., Bruno Castro da Silva, Christoph Dann, & Emma Brunskill. (2016). Energetic natural gradient descent. International Conference on Machine Learning. 2887–2895. 2 indexed citations

12.

Theocharous, Georgios, Philip S. Thomas, & Mohammad Ghavamzadeh. (2015). Personalized ad recommendation systems for life-time value optimization with guarantees. International Conference on Artificial Intelligence. 1806–1812. 26 indexed citations

13.

Thomas, Philip S., Georgios Theocharous, & Mohammad Ghavamzadeh. (2015). High Confidence Policy Improvement. International Conference on Machine Learning. 2380–2388. 32 indexed citations

14.

Thomas, Philip S., Scott Niekum, Georgios Theocharous, & George Konidaris. (2015). Policy evaluation using the Ω-return. Neural Information Processing Systems. 28. 334–342. 1 indexed citations

15.

Thomas, Philip S.. (2014). GeNGA: A Generalization of Natural Gradient Ascent with Positive and Negative Convergence Results. International Conference on Machine Learning. 1575–1583. 8 indexed citations

16.

Thomas, Philip S.. (2014). GeNGA: a generalization of natural gradient ascent with positive and. International Conference on Machine Learning. 1 indexed citations

17.

Thomas, Philip S., et al.. (2013). Projected Natural Actor-Critic. Neural Information Processing Systems. 26. 2337–2345. 9 indexed citations

18.

Thomas, Philip S.. (2011). Policy Gradient Coagent Networks. Neural Information Processing Systems. 24. 1944–1952. 3 indexed citations

19.

Thomas, Philip S. & Andrew G. Barto. (2011). Conjugate Markov Decision Processes. International Conference on Machine Learning. 137–144. 8 indexed citations

20.

Thomas, Philip S.. (1966). Import Licensing and Import Liberalization in Pakistan. The Pakistan Development Review. 500–544. 5 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.

Explore authors with similar magnitude of impact