Difference between revisions of "Doina Precup"
GerdIsenberg (talk | contribs) (Created page with "'''Home * People * Doina Precup''' FILE:DoinaPrecup.jpg|border|right|thumb|link=https://www.cs.mcgill.ca/~dprecup/| Doina Precup <ref>[https://www.cs.mcg...") |
GerdIsenberg (talk | contribs) |
||
| (One intermediate revision by the same user not shown) | |||
| Line 25: | Line 25: | ||
* [https://scholar.google.com/citations?user=jn5r6TsAAAAJ&hl=en Pablo Samuel Castro], [[Doina Precup]] ('''2010'''). ''[https://link.springer.com/chapter/10.1007/978-3-642-15880-3_19 Smarter Sampling in Model-Based Bayesian Reinforcement Learning]''. [https://dblp.uni-trier.de/db/conf/pkdd/pkdd2010-1.html#CastroP10 PKDD/ECML 2010] | * [https://scholar.google.com/citations?user=jn5r6TsAAAAJ&hl=en Pablo Samuel Castro], [[Doina Precup]] ('''2010'''). ''[https://link.springer.com/chapter/10.1007/978-3-642-15880-3_19 Smarter Sampling in Model-Based Bayesian Reinforcement Learning]''. [https://dblp.uni-trier.de/db/conf/pkdd/pkdd2010-1.html#CastroP10 PKDD/ECML 2010] | ||
* [https://github.com/kuleshov Volodymyr Kuleshov], [[Doina Precup]] ('''2014'''). ''Algorithms for multi-armed bandit problems''. [https://arxiv.org/abs/1402.6028 arXiv:1402.6028] | * [https://github.com/kuleshov Volodymyr Kuleshov], [[Doina Precup]] ('''2014'''). ''Algorithms for multi-armed bandit problems''. [https://arxiv.org/abs/1402.6028 arXiv:1402.6028] | ||
| + | * [https://scholar.google.ca/citations?user=yVtSOt8AAAAJ&hl=en Emmanuel Bengio], [https://scholar.google.ca/citations?user=9H77FYYAAAAJ&hl=en Pierre-Luc Bacon], [[Joelle Pineau]], [[Doina Precup]] ('''2015'''). ''Conditional Computation in Neural Networks for faster models''. [https://arxiv.org/abs/1511.06297 arXiv:1511.06297] | ||
* [https://scholar.google.com/citations?user=dy_JBs0AAAAJ&hl=en Peter Henderson], [https://scholar.google.ca/citations?user=2_4Rs44AAAAJ&hl=en Riashat Islam], [[Philip Bachman]], [[Joelle Pineau]], [[Doina Precup]], [https://scholar.google.ca/citations?user=gFwEytkAAAAJ&hl=en David Meger] ('''2017'''). ''Deep Reinforcement Learning that Matters''. [https://arxiv.org/abs/1709.06560 arXiv:1709.06560] | * [https://scholar.google.com/citations?user=dy_JBs0AAAAJ&hl=en Peter Henderson], [https://scholar.google.ca/citations?user=2_4Rs44AAAAJ&hl=en Riashat Islam], [[Philip Bachman]], [[Joelle Pineau]], [[Doina Precup]], [https://scholar.google.ca/citations?user=gFwEytkAAAAJ&hl=en David Meger] ('''2017'''). ''Deep Reinforcement Learning that Matters''. [https://arxiv.org/abs/1709.06560 arXiv:1709.06560] | ||
* [http://www.peterhenderson.co/ Peter Henderson], [https://scholar.google.ca/citations?user=2_4Rs44AAAAJ&hl=en Riashat Islam], [[Philip Bachman]], [[Joelle Pineau]], [[Doina Precup]], [https://scholar.google.ca/citations?user=gFwEytkAAAAJ&hl=en David Meger] ('''2017'''). ''Deep Reinforcement Learning that Matters''. [https://arxiv.org/abs/1709.06560 arXiv:1709.06560] | * [http://www.peterhenderson.co/ Peter Henderson], [https://scholar.google.ca/citations?user=2_4Rs44AAAAJ&hl=en Riashat Islam], [[Philip Bachman]], [[Joelle Pineau]], [[Doina Precup]], [https://scholar.google.ca/citations?user=gFwEytkAAAAJ&hl=en David Meger] ('''2017'''). ''Deep Reinforcement Learning that Matters''. [https://arxiv.org/abs/1709.06560 arXiv:1709.06560] | ||
* [https://scholar.google.com/citations?user=1Nk3WZoAAAAJ&hl=en Scott Fujimoto], [https://scholar.google.ca/citations?user=gFwEytkAAAAJ&hl=en David Meger], [[Doina Precup]] ('''2018'''). ''Off-Policy Deep Reinforcement Learning without Exploration''. [https://arxiv.org/abs/1812.02900 arXiv:1812.02900] | * [https://scholar.google.com/citations?user=1Nk3WZoAAAAJ&hl=en Scott Fujimoto], [https://scholar.google.ca/citations?user=gFwEytkAAAAJ&hl=en David Meger], [[Doina Precup]] ('''2018'''). ''Off-Policy Deep Reinforcement Learning without Exploration''. [https://arxiv.org/abs/1812.02900 arXiv:1812.02900] | ||
==2020 ...== | ==2020 ...== | ||
| + | * [https://scholar.google.ca/citations?user=yVtSOt8AAAAJ&hl=en Emmanuel Bengio], [[Joelle Pineau]], [[Doina Precup]] ('''2020'''). ''Interference and Generalization in Temporal Difference Learning''. [https://arxiv.org/abs/2003.06350 arXiv:2003.06350] | ||
* [https://scholar.google.com/citations?user=HT85tXsAAAAJ&hl=en Mohammad Pezeshki], [https://scholar.google.com/citations?user=jKqh8jAAAAAJ&hl=en Sékou-Oumar Kaba], [[Mathematician#YBengio|Yoshua Bengio]] , [[Mathematician#ACourville|Aaron Courville]] , [[Doina Precup]], [https://scholar.google.com/citations?user=ifu_7_0AAAAJ&hl=en Guillaume Lajoie] ('''2020'''). ''Gradient Starvation: A Learning Proclivity in Neural Networks''. [https://arxiv.org/abs/2011.09468 arXiv:2011.09468] | * [https://scholar.google.com/citations?user=HT85tXsAAAAJ&hl=en Mohammad Pezeshki], [https://scholar.google.com/citations?user=jKqh8jAAAAAJ&hl=en Sékou-Oumar Kaba], [[Mathematician#YBengio|Yoshua Bengio]] , [[Mathematician#ACourville|Aaron Courville]] , [[Doina Precup]], [https://scholar.google.com/citations?user=ifu_7_0AAAAJ&hl=en Guillaume Lajoie] ('''2020'''). ''Gradient Starvation: A Learning Proclivity in Neural Networks''. [https://arxiv.org/abs/2011.09468 arXiv:2011.09468] | ||
Latest revision as of 23:04, 12 April 2021
Doina Precup [1]
Doina Precup,
an Romanian computer scientist and Ph.D. in Computer Science from the University of Massachusetts,
Amherst under advisor Richard Sutton in 2000 [2].
She defended her B.Sc. and M.Sc. degrees in computer science and engineering at the Technical University of Cluj-Napoca in 1994 and 1995 respectively.
In July 2000, she joined the School of Computer Science at McGill University, and is also affiliated with DeepMind. Doina Precup’s research interests lie mainly in the field of machine learning.
She is especially interested in the learning problems that face a decision-maker interacting with a complex, uncertain environment [3] .
Contents
Selected Publications
1997 ...
- Doina Precup, Richard Sutton (1997). Multi-time Models for Temporally Abstract Planning. NIPS 1997, pdf
- Paul E. Utgoff, Doina Precup (1998). Constructive Function Approximation. Feature Extraction, Construction, and Selection: A Data-Mining Perspective. Kluwer
- Richard Sutton, Doina Precup, Satinder Singh (1999). Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence, Vol. 112, pdf
2000 ...
- Doina Precup (2000). Temporal Abstraction in Reinforcement Learning. Ph.D. thesis, University of Massachusetts, Amherst.
- Doina Precup, Paul E. Utgoff (2004). Classification using Phi-Machines and Constructive Function Approximation. Machine Learning, Vol. 55
- Hamid Reza Maei, Csaba Szepesvári, Shalabh Bhatnagar, Doina Precup, David Silver, Richard Sutton (2009). Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation. NIPS 2009, pdf
- Richard Sutton, Hamid Reza Maei, Doina Precup, Shalabh Bhatnagar, David Silver, Csaba Szepesvári, Eric Wiewiora. (2009). Fast Gradient-Descent Methods for Temporal-Difference Learning with Linear Function Approximation. ICML 2009
- Robert West, Joelle Pineau, Doina Precup (2009). Wikispeedia: An Online Game for Inferring Semantic Distances between Concepts. IJCAI 2009
2010 ...
- Pablo Samuel Castro, Doina Precup (2010). Smarter Sampling in Model-Based Bayesian Reinforcement Learning. PKDD/ECML 2010
- Volodymyr Kuleshov, Doina Precup (2014). Algorithms for multi-armed bandit problems. arXiv:1402.6028
- Emmanuel Bengio, Pierre-Luc Bacon, Joelle Pineau, Doina Precup (2015). Conditional Computation in Neural Networks for faster models. arXiv:1511.06297
- Peter Henderson, Riashat Islam, Philip Bachman, Joelle Pineau, Doina Precup, David Meger (2017). Deep Reinforcement Learning that Matters. arXiv:1709.06560
- Peter Henderson, Riashat Islam, Philip Bachman, Joelle Pineau, Doina Precup, David Meger (2017). Deep Reinforcement Learning that Matters. arXiv:1709.06560
- Scott Fujimoto, David Meger, Doina Precup (2018). Off-Policy Deep Reinforcement Learning without Exploration. arXiv:1812.02900
2020 ...
- Emmanuel Bengio, Joelle Pineau, Doina Precup (2020). Interference and Generalization in Temporal Difference Learning. arXiv:2003.06350
- Mohammad Pezeshki, Sékou-Oumar Kaba, Yoshua Bengio , Aaron Courville , Doina Precup, Guillaume Lajoie (2020). Gradient Starvation: A Learning Proclivity in Neural Networks. arXiv:2011.09468
External Links
- Doina Precup - Wikipedia
- Doina Precup - Mila
- Doina Precup's Home Page
- The Mathematics Genealogy Project - Doina Precup
- Doina Precup - Google Scholar
