25,161
edits
Changes
Created page with "'''Home * People * Christopher D. Rosin''' FILE:ChrisRosin.jpg|border|right|thumb|link=http://www.chrisrosin.com/|Christopher D. Rosin <ref>[http://www.ch..."
'''[[Main Page|Home]] * [[People]] * Christopher D. Rosin'''
[[FILE:ChrisRosin.jpg|border|right|thumb|link=http://www.chrisrosin.com/|Christopher D. Rosin <ref>[http://www.chrisrosin.com/ Chris Rosin]</ref> ]]
'''Christopher Darrell (Chris) Rosin''',<br/>
an American computer scientist working in the fields of [[Learning|machine learning]] and [https://en.wikipedia.org/wiki/Monitoring_(medicine) medical monitoring], as well as computer [[Go]] programmer. He defended his Ph.D. in 1997 at [https://en.wikipedia.org/wiki/University_of_California,_San_Diego University of California, San Diego] on the topic of [[Genetic Programming#GeneticAlgorithm|genetic algorithms]] <ref>[[Christopher D. Rosin]] ('''1997'''). ''Coevolutionary Search Among Adversaries''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_California,_San_Diego University of California, San Diego], [http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.26.6404 CiteSeerX]</ref>.
=PUCT=
As author of the [[Go]] playing program ''Greenpeep'' <ref>[http://www.chrisrosin.com/greenpeep/index.html Greenpeep, a Computer Go Program]</ref>, Chris Rosin devised an improvement of [[UCT]] dubbed '''PUCT''', as implemented in his program, the idea further published and elaborated in ''Multi-armed bandits with episode context'' <ref>[[Christopher D. Rosin]] ('''2011'''). ''[https://link.springer.com/article/10.1007/s10472-011-9258-6 Multi-armed bandits with episode context]''. Annals of Mathematics and Artificial Intelligence, Vol. 61, No. 3, [http://gauss.ececs.uc.edu/Workshops/isaim2010/papers/rosin.pdf ISAIM 2010 pdf]</ref>. PUCT modifies the original UCB1 multi-armed bandit policy by approximately predicting good arms at the start of a sequence of multi-armed bandit trials ('Predictor' + UCB = PUCB). A variation of PUCT was used in the [[AlphaGo]] and [[AlphaZero]] projects <ref>[[David Silver]], [[Shih-Chieh Huang|Aja Huang]], [[Chris J. Maddison]], [[Arthur Guez]], [[Laurent Sifre]], [[George van den Driessche]], [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Veda Panneershelvam]], [[Marc Lanctot]], [[Sander Dieleman]], [[Dominik Grewe]], [[John Nham]], [[Nal Kalchbrenner]], [[Ilya Sutskever]], [[Timothy Lillicrap]], [[Madeleine Leach]], [[Koray Kavukcuoglu]], [[Thore Graepel]], [[Demis Hassabis]] ('''2016'''). ''[http://www.nature.com/nature/journal/v529/n7587/full/nature16961.html Mastering the game of Go with deep neural networks and tree search]''. [https://en.wikipedia.org/wiki/Nature_%28journal%29 Nature], Vol. 529</ref> , and subsequently also in [[Leela Zero]] and [[Leela Chess Zero]] <ref>[https://github.com/LeelaChessZero/lc0/wiki/FAQ FAQ · LeelaChessZero/lc0 Wiki · GitHub]</ref>.
=Selected Publications=
<ref>[http://www.chrisrosin.com/ Chris Rosin]</ref> <ref>[https://dblp.uni-trier.de/pers/hd/r/Rosin:Christopher_D= dblp: Christopher D. Rosin]</ref>
==1995 ...==
* [[Christopher D. Rosin]], [https://scholar.google.com/citations?user=vqrY_hgAAAAJ&hl=en Richard K. Belew] ('''1995'''). ''Methods for Competitive Co-Evolution: Finding Opponents Worth Beating''. [https://dblp.uni-trier.de/db/conf/icga/icga1995.html ICGA 1995], [http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.52.9359 CiteSeerX]
* [[Christopher D. Rosin]], [https://scholar.google.com/citations?user=vqrY_hgAAAAJ&hl=en Richard K. Belew] ('''1996'''). ''A Competitive Approach in Game Learning''. [https://dblp.uni-trier.de/db/conf/colt/colt1996.html COLT 1996], [http://www.sci.brooklyn.cuny.edu/~sklar/teaching/f05/alife/papers/rosin-96competitive.pdf pdf]
* [[Christopher D. Rosin]] ('''1997'''). ''Coevolutionary Search Among Adversaries''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_California,_San_Diego University of California, San Diego], [http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.26.6404 CiteSeerX]
==2000 ...==
* [[Christopher D. Rosin]] ('''2000'''). ''[https://www.sciencedirect.com/science/article/pii/S0022000099916446 Sample Complexity of Model-Based Search]''. [https://en.wikipedia.org/wiki/Journal_of_Computer_and_System_Sciences Journal of Computer and System Sciences], Vol. 60, No. 2
==2010 ...==
* [[Christopher D. Rosin]] ('''2011'''). ''[https://link.springer.com/article/10.1007/s10472-011-9258-6 Multi-armed bandits with episode context]''. Annals of Mathematics and Artificial Intelligence, Vol. 61, No. 3, [http://gauss.ececs.uc.edu/Workshops/isaim2010/papers/rosin.pdf ISAIM 2010 pdf]
* [[Christopher D. Rosin]] ('''2011'''). '' Nested Rollout Policy Adaptation for Monte Carlo Tree Search''. [[Conferences#IJCAI2011|IJCAI 2011]], [http://www.chrisrosin.com/rosin-ijcai11.pdf pdf]
* [[Christopher D. Rosin]] ('''2014'''). ''Game playing''. [https://en.wikipedia.org/wiki/Wiley_Interdisciplinary_Reviews:_Cognitive_Science WIREs Cognitive Science], Vol. 5, [http://www.chrisrosin.com/Rosin-Game-Playing-submitted-ver.pdf pdf preprint]
=External Links=
* [http://www.chrisrosin.com/ Chris Rosin]
* [http://www.chrisrosin.com/greenpeep/index.html Greenpeep, a Computer Go Program]
=References=
<references />
'''[[People|Up one level]]'''
[[FILE:ChrisRosin.jpg|border|right|thumb|link=http://www.chrisrosin.com/|Christopher D. Rosin <ref>[http://www.chrisrosin.com/ Chris Rosin]</ref> ]]
'''Christopher Darrell (Chris) Rosin''',<br/>
an American computer scientist working in the fields of [[Learning|machine learning]] and [https://en.wikipedia.org/wiki/Monitoring_(medicine) medical monitoring], as well as computer [[Go]] programmer. He defended his Ph.D. in 1997 at [https://en.wikipedia.org/wiki/University_of_California,_San_Diego University of California, San Diego] on the topic of [[Genetic Programming#GeneticAlgorithm|genetic algorithms]] <ref>[[Christopher D. Rosin]] ('''1997'''). ''Coevolutionary Search Among Adversaries''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_California,_San_Diego University of California, San Diego], [http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.26.6404 CiteSeerX]</ref>.
=PUCT=
As author of the [[Go]] playing program ''Greenpeep'' <ref>[http://www.chrisrosin.com/greenpeep/index.html Greenpeep, a Computer Go Program]</ref>, Chris Rosin devised an improvement of [[UCT]] dubbed '''PUCT''', as implemented in his program, the idea further published and elaborated in ''Multi-armed bandits with episode context'' <ref>[[Christopher D. Rosin]] ('''2011'''). ''[https://link.springer.com/article/10.1007/s10472-011-9258-6 Multi-armed bandits with episode context]''. Annals of Mathematics and Artificial Intelligence, Vol. 61, No. 3, [http://gauss.ececs.uc.edu/Workshops/isaim2010/papers/rosin.pdf ISAIM 2010 pdf]</ref>. PUCT modifies the original UCB1 multi-armed bandit policy by approximately predicting good arms at the start of a sequence of multi-armed bandit trials ('Predictor' + UCB = PUCB). A variation of PUCT was used in the [[AlphaGo]] and [[AlphaZero]] projects <ref>[[David Silver]], [[Shih-Chieh Huang|Aja Huang]], [[Chris J. Maddison]], [[Arthur Guez]], [[Laurent Sifre]], [[George van den Driessche]], [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Veda Panneershelvam]], [[Marc Lanctot]], [[Sander Dieleman]], [[Dominik Grewe]], [[John Nham]], [[Nal Kalchbrenner]], [[Ilya Sutskever]], [[Timothy Lillicrap]], [[Madeleine Leach]], [[Koray Kavukcuoglu]], [[Thore Graepel]], [[Demis Hassabis]] ('''2016'''). ''[http://www.nature.com/nature/journal/v529/n7587/full/nature16961.html Mastering the game of Go with deep neural networks and tree search]''. [https://en.wikipedia.org/wiki/Nature_%28journal%29 Nature], Vol. 529</ref> , and subsequently also in [[Leela Zero]] and [[Leela Chess Zero]] <ref>[https://github.com/LeelaChessZero/lc0/wiki/FAQ FAQ · LeelaChessZero/lc0 Wiki · GitHub]</ref>.
=Selected Publications=
<ref>[http://www.chrisrosin.com/ Chris Rosin]</ref> <ref>[https://dblp.uni-trier.de/pers/hd/r/Rosin:Christopher_D= dblp: Christopher D. Rosin]</ref>
==1995 ...==
* [[Christopher D. Rosin]], [https://scholar.google.com/citations?user=vqrY_hgAAAAJ&hl=en Richard K. Belew] ('''1995'''). ''Methods for Competitive Co-Evolution: Finding Opponents Worth Beating''. [https://dblp.uni-trier.de/db/conf/icga/icga1995.html ICGA 1995], [http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.52.9359 CiteSeerX]
* [[Christopher D. Rosin]], [https://scholar.google.com/citations?user=vqrY_hgAAAAJ&hl=en Richard K. Belew] ('''1996'''). ''A Competitive Approach in Game Learning''. [https://dblp.uni-trier.de/db/conf/colt/colt1996.html COLT 1996], [http://www.sci.brooklyn.cuny.edu/~sklar/teaching/f05/alife/papers/rosin-96competitive.pdf pdf]
* [[Christopher D. Rosin]] ('''1997'''). ''Coevolutionary Search Among Adversaries''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_California,_San_Diego University of California, San Diego], [http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.26.6404 CiteSeerX]
==2000 ...==
* [[Christopher D. Rosin]] ('''2000'''). ''[https://www.sciencedirect.com/science/article/pii/S0022000099916446 Sample Complexity of Model-Based Search]''. [https://en.wikipedia.org/wiki/Journal_of_Computer_and_System_Sciences Journal of Computer and System Sciences], Vol. 60, No. 2
==2010 ...==
* [[Christopher D. Rosin]] ('''2011'''). ''[https://link.springer.com/article/10.1007/s10472-011-9258-6 Multi-armed bandits with episode context]''. Annals of Mathematics and Artificial Intelligence, Vol. 61, No. 3, [http://gauss.ececs.uc.edu/Workshops/isaim2010/papers/rosin.pdf ISAIM 2010 pdf]
* [[Christopher D. Rosin]] ('''2011'''). '' Nested Rollout Policy Adaptation for Monte Carlo Tree Search''. [[Conferences#IJCAI2011|IJCAI 2011]], [http://www.chrisrosin.com/rosin-ijcai11.pdf pdf]
* [[Christopher D. Rosin]] ('''2014'''). ''Game playing''. [https://en.wikipedia.org/wiki/Wiley_Interdisciplinary_Reviews:_Cognitive_Science WIREs Cognitive Science], Vol. 5, [http://www.chrisrosin.com/Rosin-Game-Playing-submitted-ver.pdf pdf preprint]
=External Links=
* [http://www.chrisrosin.com/ Chris Rosin]
* [http://www.chrisrosin.com/greenpeep/index.html Greenpeep, a Computer Go Program]
=References=
<references />
'''[[People|Up one level]]'''
