25,161
edits
Changes
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..."
'''[[Main Page|Home]] * [[People]] * Doina Precup'''
[[FILE:DoinaPrecup.jpg|border|right|thumb|link=https://www.cs.mcgill.ca/~dprecup/| Doina Precup <ref>[https://www.cs.mcgill.ca/~dprecup/ Doina Precup's Home Page]</ref> ]]
'''Doina Precup''',<br/>
an Romanian computer scientist and Ph.D. in Computer Science from the [https://en.wikipedia.org/wiki/University_of_Massachusetts_Amherst University of Massachusetts],
[https://en.wikipedia.org/wiki/Amherst,_Massachusetts Amherst] under advisor [[Richard Sutton]] in 2000 <ref>[https://www.mathgenealogy.org/id.php?id=122264 The Mathematics Genealogy Project - Doina Precup]</ref>.
She defended her B.Sc. and M.Sc. degrees in computer science and engineering at the [https://en.wikipedia.org/wiki/Technical_University_of_Cluj-Napoca 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 [[Learning|machine learning]].
She is especially interested in the learning problems that face a decision-maker interacting with a complex, uncertain environment <ref>[http://www.jot.fm/issues/issue_2004_04/article13/ JOT: Journal of Object Technology - Improving Rule Set Based Software Quality Prediction: A Genetic Algorithm-based Approach]</ref> .
=Selected Publications=
<ref>[https://dblp.uni-trier.de/pid/p/DoinaPrecup.html dblp: Doina Precup]</ref>
==1997 ...==
* [[Doina Precup]], [[Richard Sutton]] ('''1997'''). ''Multi-time Models for Temporally Abstract Planning''. [https://dblp.uni-trier.de/db/conf/nips/nips1997.html#PrecupS97 NIPS 1997], [https://papers.nips.cc/paper/1997/file/a9be4c2a4041cadbf9d61ae16dd1389e-Paper.pdf pdf]
* [[Paul E. Utgoff]], [[Doina Precup]] ('''1998'''). ''[https://link.springer.com/chapter/10.1007/978-1-4615-5725-8_14 Constructive Function Approximation]''. [https://link.springer.com/book/10.1007/978-1-4615-5725-8 Feature Extraction, Construction, and Selection: A Data-Mining Perspective]. [https://en.wikipedia.org/wiki/Wolters_Kluwer Kluwer]
* [[Richard Sutton]], [[Doina Precup]], [[Mathematician#SSingh|Satinder Singh]] ('''1999'''). ''Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning''. [https://en.wikipedia.org/wiki/Artificial_Intelligence_(journal) Artificial Intelligence], Vol. 112, [https://people.cs.umass.edu/~barto/courses/cs687/Sutton-Precup-Singh-AIJ99.pdf pdf]
==2000 ...==
* [[Doina Precup]] ('''2000'''). ''[https://scholarworks.umass.edu/dissertations/AAI9978540/ Temporal Abstraction in Reinforcement Learning]''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_Massachusetts_Amherst University of Massachusetts], [https://en.wikipedia.org/wiki/Amherst,_Massachusetts Amherst].
* [[Doina Precup]], [[Paul E. Utgoff]] ('''2004'''). ''Classification using Phi-Machines and Constructive Function Approximation''. [https://en.wikipedia.org/wiki/Machine_Learning_%28journal%29 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''. [https://dblp.uni-trier.de/db/conf/nips/nips2009.html#MaeiSBPSS09 NIPS 2009], [https://papers.nips.cc/paper/2009/file/3a15c7d0bbe60300a39f76f8a5ba6896-Paper.pdf pdf]
* [[Richard Sutton]], [[Hamid Reza Maei]], [[Doina Precup]], [[Shalabh Bhatnagar]], [[David Silver]], [[Csaba Szepesvári]], [[Eric Wiewiora]]. ('''2009'''). ''[https://dl.acm.org/doi/10.1145/1553374.1553501 Fast Gradient-Descent Methods for Temporal-Difference Learning with Linear Function Approximation]''. [https://dblp.uni-trier.de/db/conf/icml/icml2009.html#SuttonMPBSSW09 ICML 2009]
* [https://scholar.google.com/citations?user=ZiFn598AAAAJ Robert West], [[Joelle Pineau]], [[Doina Precup]] ('''2009'''). ''[https://www.semanticscholar.org/paper/Wikispeedia%3A-An-Online-Game-for-Inferring-Semantic-West-Pineau/bfda484fe2860682f1b8410e1f0835562eba2662 Wikispeedia: An Online Game for Inferring Semantic Distances between Concepts]''. [[Conferences#IJCAI2009|IJCAI 2009]]
==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://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]
* [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 ...==
* [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]
=External Links=
* [https://en.wikipedia.org/wiki/Doina_Precup Doina Precup - Wikipedia]
* [https://mila.quebec/en/person/doina-precup/ Doina Precup - Mila]
* [https://www.cs.mcgill.ca/~dprecup/ Doina Precup's Home Page]
* [https://www.mathgenealogy.org/id.php?id=122264 The Mathematics Genealogy Project - Doina Precup]
* [https://scholar.google.com/citations?user=j54VcVEAAAAJ&hl=en Doina Precup - Google Scholar]
=References=
<references />
'''[[People|Up one level]]'''
[[Category:Researcher|Precup]]
[[FILE:DoinaPrecup.jpg|border|right|thumb|link=https://www.cs.mcgill.ca/~dprecup/| Doina Precup <ref>[https://www.cs.mcgill.ca/~dprecup/ Doina Precup's Home Page]</ref> ]]
'''Doina Precup''',<br/>
an Romanian computer scientist and Ph.D. in Computer Science from the [https://en.wikipedia.org/wiki/University_of_Massachusetts_Amherst University of Massachusetts],
[https://en.wikipedia.org/wiki/Amherst,_Massachusetts Amherst] under advisor [[Richard Sutton]] in 2000 <ref>[https://www.mathgenealogy.org/id.php?id=122264 The Mathematics Genealogy Project - Doina Precup]</ref>.
She defended her B.Sc. and M.Sc. degrees in computer science and engineering at the [https://en.wikipedia.org/wiki/Technical_University_of_Cluj-Napoca 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 [[Learning|machine learning]].
She is especially interested in the learning problems that face a decision-maker interacting with a complex, uncertain environment <ref>[http://www.jot.fm/issues/issue_2004_04/article13/ JOT: Journal of Object Technology - Improving Rule Set Based Software Quality Prediction: A Genetic Algorithm-based Approach]</ref> .
=Selected Publications=
<ref>[https://dblp.uni-trier.de/pid/p/DoinaPrecup.html dblp: Doina Precup]</ref>
==1997 ...==
* [[Doina Precup]], [[Richard Sutton]] ('''1997'''). ''Multi-time Models for Temporally Abstract Planning''. [https://dblp.uni-trier.de/db/conf/nips/nips1997.html#PrecupS97 NIPS 1997], [https://papers.nips.cc/paper/1997/file/a9be4c2a4041cadbf9d61ae16dd1389e-Paper.pdf pdf]
* [[Paul E. Utgoff]], [[Doina Precup]] ('''1998'''). ''[https://link.springer.com/chapter/10.1007/978-1-4615-5725-8_14 Constructive Function Approximation]''. [https://link.springer.com/book/10.1007/978-1-4615-5725-8 Feature Extraction, Construction, and Selection: A Data-Mining Perspective]. [https://en.wikipedia.org/wiki/Wolters_Kluwer Kluwer]
* [[Richard Sutton]], [[Doina Precup]], [[Mathematician#SSingh|Satinder Singh]] ('''1999'''). ''Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning''. [https://en.wikipedia.org/wiki/Artificial_Intelligence_(journal) Artificial Intelligence], Vol. 112, [https://people.cs.umass.edu/~barto/courses/cs687/Sutton-Precup-Singh-AIJ99.pdf pdf]
==2000 ...==
* [[Doina Precup]] ('''2000'''). ''[https://scholarworks.umass.edu/dissertations/AAI9978540/ Temporal Abstraction in Reinforcement Learning]''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_Massachusetts_Amherst University of Massachusetts], [https://en.wikipedia.org/wiki/Amherst,_Massachusetts Amherst].
* [[Doina Precup]], [[Paul E. Utgoff]] ('''2004'''). ''Classification using Phi-Machines and Constructive Function Approximation''. [https://en.wikipedia.org/wiki/Machine_Learning_%28journal%29 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''. [https://dblp.uni-trier.de/db/conf/nips/nips2009.html#MaeiSBPSS09 NIPS 2009], [https://papers.nips.cc/paper/2009/file/3a15c7d0bbe60300a39f76f8a5ba6896-Paper.pdf pdf]
* [[Richard Sutton]], [[Hamid Reza Maei]], [[Doina Precup]], [[Shalabh Bhatnagar]], [[David Silver]], [[Csaba Szepesvári]], [[Eric Wiewiora]]. ('''2009'''). ''[https://dl.acm.org/doi/10.1145/1553374.1553501 Fast Gradient-Descent Methods for Temporal-Difference Learning with Linear Function Approximation]''. [https://dblp.uni-trier.de/db/conf/icml/icml2009.html#SuttonMPBSSW09 ICML 2009]
* [https://scholar.google.com/citations?user=ZiFn598AAAAJ Robert West], [[Joelle Pineau]], [[Doina Precup]] ('''2009'''). ''[https://www.semanticscholar.org/paper/Wikispeedia%3A-An-Online-Game-for-Inferring-Semantic-West-Pineau/bfda484fe2860682f1b8410e1f0835562eba2662 Wikispeedia: An Online Game for Inferring Semantic Distances between Concepts]''. [[Conferences#IJCAI2009|IJCAI 2009]]
==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://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]
* [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 ...==
* [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]
=External Links=
* [https://en.wikipedia.org/wiki/Doina_Precup Doina Precup - Wikipedia]
* [https://mila.quebec/en/person/doina-precup/ Doina Precup - Mila]
* [https://www.cs.mcgill.ca/~dprecup/ Doina Precup's Home Page]
* [https://www.mathgenealogy.org/id.php?id=122264 The Mathematics Genealogy Project - Doina Precup]
* [https://scholar.google.com/citations?user=j54VcVEAAAAJ&hl=en Doina Precup - Google Scholar]
=References=
<references />
'''[[People|Up one level]]'''
[[Category:Researcher|Precup]]
