Difference between revisions of "Reinforcement Learning"

From Chessprogramming wiki
Jump to: navigation, search
(42 intermediate revisions by the same user not shown)
Line 9: Line 9:
  
 
=Q-Learning=
 
=Q-Learning=
Q-Learning, introduced by [[Chris Watkins]] in 1989, is a simple way for [https://en.wikipedia.org/wiki/Intelligent_agent agents] to learn how to act optimally in controlled Markovian domains <ref>[https://en.wikipedia.org/wiki/Q-learning Q-learning from Wikipedia]</ref>. It amounts to an incremental method for dynamic programming which imposes limited computational demands. It works by successively improving its evaluations of the quality of particular actions at particular states. Q-learning converges to the optimum action-values with probability 1 so long as all actions are repeatedly sampled in all states and the action-values are represented discretely <ref>[[Chris Watkins]], [[Peter Dayan]] ('''1992'''). ''[http://www.gatsby.ucl.ac.uk/~dayan/papers/wd92.html Q-learning]''. [https://en.wikipedia.org/wiki/Machine_Learning_(journal) Machine Learning], Vol. 8, No. 2</ref>. Q-learning has been successfully applied to [[Deep Learning|deep learning]] by a [[Google]] [[DeepMind]] team in playing some [[Atari 8-bit|Atari 2600]] [https://en.wikipedia.org/wiki/List_of_Atari_2600_games games] as published in [https://en.wikipedia.org/wiki/Nature_%28journal%29 Nature], 2015, dubbed ''deep reinforcement learning'' or ''deep Q-networks'' <ref>[[Volodymyr Mnih]], [[Koray Kavukcuoglu]], [[David Silver]], [[Andrei A. Rusu]], [[Joel Veness]], [[Marc G. Bellemare]], [[Alex Graves]], [[Martin Riedmiller]], [[Andreas K. Fidjeland]], [[Georg Ostrovski]], [[Stig Petersen]], [[Charles Beattie]], [[Amir Sadik]], [[Ioannis Antonoglou]], [[Helen King]], [[Dharshan Kumaran]], [[Daan Wierstra]], [[Shane Legg]], [[Demis Hassabis]] ('''2015'''). ''[http://www.nature.com/nature/journal/v518/n7540/abs/nature14236.html Human-level control through deep reinforcement learning]''. [https://en.wikipedia.org/wiki/Nature_%28journal%29 Nature], Vol. 518</ref>, soon followed by the spectacular [[AlphaGo]] and [[AlphaZero]] breakthroughs.  
+
Q-Learning, introduced by [[Chris Watkins]] in 1989, is a simple way for [https://en.wikipedia.org/wiki/Intelligent_agent agents] to learn how to act optimally in controlled Markovian domains <ref>[https://en.wikipedia.org/wiki/Q-learning Q-learning from Wikipedia]</ref>. It amounts to an incremental method for dynamic programming which imposes limited computational demands. It works by successively improving its evaluations of the quality of particular actions at particular states. Q-learning converges to the optimum action-values with probability 1 so long as all actions are repeatedly sampled in all states and the action-values are represented discretely <ref>[[Chris Watkins]], [[Peter Dayan]] ('''1992'''). ''[http://www.gatsby.ucl.ac.uk/~dayan/papers/wd92.html Q-learning]''. [https://en.wikipedia.org/wiki/Machine_Learning_(journal) Machine Learning], Vol. 8, No. 2</ref>. Q-learning has been successfully applied to [[Deep Learning|deep learning]] by a [[Google]] [[DeepMind]] team in playing some [[Atari 8-bit|Atari 2600]] [https://en.wikipedia.org/wiki/List_of_Atari_2600_games games] as published in [https://en.wikipedia.org/wiki/Nature_%28journal%29 Nature], 2015, dubbed ''deep reinforcement learning'' or ''deep Q-networks'' <ref>[[Volodymyr Mnih]], [[Koray Kavukcuoglu]], [[David Silver]], [[Mathematician#AARusu|Andrei A. Rusu]], [[Joel Veness]], [[Marc G. Bellemare]], [[Alex Graves]], [[Martin Riedmiller]], [[Andreas K. Fidjeland]], [[Georg Ostrovski]], [[Stig Petersen]], [[Charles Beattie]], [[Amir Sadik]], [[Ioannis Antonoglou]], [[Helen King]], [[Dharshan Kumaran]], [[Daan Wierstra]], [[Shane Legg]], [[Demis Hassabis]] ('''2015'''). ''[http://www.nature.com/nature/journal/v518/n7540/abs/nature14236.html Human-level control through deep reinforcement learning]''. [https://en.wikipedia.org/wiki/Nature_%28journal%29 Nature], Vol. 518</ref>, soon followed by the spectacular [[AlphaGo]] and [[AlphaZero]] breakthroughs.  
  
 
=Temporal Difference Learning=
 
=Temporal Difference Learning=
Line 20: Line 20:
 
=See also=
 
=See also=
 
* [[AlphaZero]]
 
* [[AlphaZero]]
 +
* [[Automated Tuning]]
 
* [[Deep Learning]]
 
* [[Deep Learning]]
 
* [[Dynamic Programming]]
 
* [[Dynamic Programming]]
Line 43: Line 44:
 
* [[A. Harry Klopf]] ('''1972'''). ''Brain Function and Adaptive Systems - A Heterostatic Theory''. [https://en.wikipedia.org/wiki/Air_Force_Cambridge_Research_Laboratories Air Force Cambridge Research Laboratories], Special Reports, No. 133, [http://www.dtic.mil/dtic/tr/fulltext/u2/742259.pdf pdf]
 
* [[A. Harry Klopf]] ('''1972'''). ''Brain Function and Adaptive Systems - A Heterostatic Theory''. [https://en.wikipedia.org/wiki/Air_Force_Cambridge_Research_Laboratories Air Force Cambridge Research Laboratories], Special Reports, No. 133, [http://www.dtic.mil/dtic/tr/fulltext/u2/742259.pdf pdf]
 
* [[Mathematician#Holland|John H. Holland]] ('''1975'''). ''Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence''. [http://www.amazon.com/Adaptation-Natural-Artificial-Systems-Introductory/dp/0262581116 amazon.com]
 
* [[Mathematician#Holland|John H. Holland]] ('''1975'''). ''Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence''. [http://www.amazon.com/Adaptation-Natural-Artificial-Systems-Introductory/dp/0262581116 amazon.com]
 +
* [[Ian H. Witten]] ('''1977'''). ''An Adaptive Optimal Controller for Discrete-Time Markov Environments''. [https://en.wikipedia.org/wiki/Information_and_Computation Information and Control], Vol. 34, No. 4, [https://core.ac.uk/download/pdf/82451748.pdf pdf]
 
==1980 ...==
 
==1980 ...==
 
* [[Richard Sutton]] ('''1984'''). ''[http://scholarworks.umass.edu/dissertations/AAI8410337/ Temporal Credit Assignment in Reinforcement Learning]''. Ph.D. dissertation, [https://en.wikipedia.org/wiki/University_of_Massachusetts University of Massachusetts]
 
* [[Richard Sutton]] ('''1984'''). ''[http://scholarworks.umass.edu/dissertations/AAI8410337/ Temporal Credit Assignment in Reinforcement Learning]''. Ph.D. dissertation, [https://en.wikipedia.org/wiki/University_of_Massachusetts University of Massachusetts]
Line 50: Line 52:
 
* [[Richard Sutton]], [[Andrew Barto]] ('''1990'''). ''Time Derivative Models of Pavlovian Reinforcement''. Learning and Computational Neuroscience: Foundations of Adaptive Networks: 497-537
 
* [[Richard Sutton]], [[Andrew Barto]] ('''1990'''). ''Time Derivative Models of Pavlovian Reinforcement''. Learning and Computational Neuroscience: Foundations of Adaptive Networks: 497-537
 
* [[Jürgen Schmidhuber]] ('''1990'''). ''Reinforcement Learning in Markovian and Non-Markovian Environments''. [https://dblp.uni-trier.de/db/conf/nips/nips1990.html NIPS 1990], [ftp://ftp.idsia.ch/pub/juergen/nipsnonmarkov.pdf pdf]
 
* [[Jürgen Schmidhuber]] ('''1990'''). ''Reinforcement Learning in Markovian and Non-Markovian Environments''. [https://dblp.uni-trier.de/db/conf/nips/nips1990.html NIPS 1990], [ftp://ftp.idsia.ch/pub/juergen/nipsnonmarkov.pdf pdf]
 +
* [[Peter Dayan]] ('''1991'''). ''[https://www.era.lib.ed.ac.uk/handle/1842/14754 Reinforcing Connectionism: Learning the Statistical Way]''. Ph.D. thesis, [[University of Edinburgh]]
 
* [[Chris Watkins]], [[Peter Dayan]] ('''1992'''). ''[http://www.gatsby.ucl.ac.uk/~dayan/papers/wd92.html Q-learning]''. [https://en.wikipedia.org/wiki/Machine_Learning_(journal) Machine Learning], Vol. 8, No. 2
 
* [[Chris Watkins]], [[Peter Dayan]] ('''1992'''). ''[http://www.gatsby.ucl.ac.uk/~dayan/papers/wd92.html Q-learning]''. [https://en.wikipedia.org/wiki/Machine_Learning_(journal) Machine Learning], Vol. 8, No. 2
 
* [[Gerald Tesauro]] ('''1992'''). ''Temporal Difference Learning of Backgammon Strategy''. [http://www.informatik.uni-trier.de/~ley/db/conf/icml/ml1992.html#Tesauro92 ML 1992]
 
* [[Gerald Tesauro]] ('''1992'''). ''Temporal Difference Learning of Backgammon Strategy''. [http://www.informatik.uni-trier.de/~ley/db/conf/icml/ml1992.html#Tesauro92 ML 1992]
Line 60: Line 63:
 
* [[Mathematician#LPKaelbling|Leslie Pack Kaelbling]], [[Michael L. Littman]], [[Mathematician#AWMoore|Andrew W. Moore]] ('''1996'''). ''[http://www.cs.washington.edu/research/jair/volume4/kaelbling96a-html/rl-survey.html Reinforcement Learning: A Survey]''. [http://www.jair.org/vol/vol4.html JAIR Vol. 4], [http://www.cs.cmu.edu/afs/cs/project/jair/pub/volume4/kaelbling96a.pdf pdf]
 
* [[Mathematician#LPKaelbling|Leslie Pack Kaelbling]], [[Michael L. Littman]], [[Mathematician#AWMoore|Andrew W. Moore]] ('''1996'''). ''[http://www.cs.washington.edu/research/jair/volume4/kaelbling96a-html/rl-survey.html Reinforcement Learning: A Survey]''. [http://www.jair.org/vol/vol4.html JAIR Vol. 4], [http://www.cs.cmu.edu/afs/cs/project/jair/pub/volume4/kaelbling96a.pdf pdf]
 
* [[Robert Levinson]] ('''1996'''). ''[http://onlinelibrary.wiley.com/doi/10.1111/j.1467-8640.1996.tb00257.x/abstract General Game-Playing and Reinforcement Learning]''.  [http://dblp.uni-trier.de/db/journals/ci/ci12.html#PellEL96 Computational Intelligence, Vol. 12], No. 1
 
* [[Robert Levinson]] ('''1996'''). ''[http://onlinelibrary.wiley.com/doi/10.1111/j.1467-8640.1996.tb00257.x/abstract General Game-Playing and Reinforcement Learning]''.  [http://dblp.uni-trier.de/db/journals/ci/ci12.html#PellEL96 Computational Intelligence, Vol. 12], No. 1
 +
* [[David E. Moriarty]], [[Risto Miikkulainen]] ('''1996'''). ''[https://link.springer.com/article/10.1023/A:1018004120707 Efficient Reinforcement Learning through Symbiotic Evolution]''. [https://en.wikipedia.org/wiki/Machine_Learning_(journal) Machine Learning], Vol. 22
 
* [[Ronald Parr]], [[Stuart Russell]] ('''1997'''). ''Reinforcement Learning with Hierarchies of Machines.'' In Advances in Neural Information Processing Systems 10, MIT Press, [http://www.cs.berkeley.edu/~russell/papers/nips97-ham.ps.gz zipped ps]
 
* [[Ronald Parr]], [[Stuart Russell]] ('''1997'''). ''Reinforcement Learning with Hierarchies of Machines.'' In Advances in Neural Information Processing Systems 10, MIT Press, [http://www.cs.berkeley.edu/~russell/papers/nips97-ham.ps.gz zipped ps]
 
* [[William Uther]], [[Manuela Veloso|Manuela M. Veloso]] ('''1997'''). ''Adversarial Reinforcement Learning''. [[Carnegie Mellon University]], [http://www.cse.unsw.edu.au/~willu/w/papers/Uther97a.ps ps]
 
* [[William Uther]], [[Manuela Veloso|Manuela M. Veloso]] ('''1997'''). ''Adversarial Reinforcement Learning''. [[Carnegie Mellon University]], [http://www.cse.unsw.edu.au/~willu/w/papers/Uther97a.ps ps]
Line 68: Line 72:
 
* [http://www.ilsp.gr/homepages/papavasiliou_eng.html Vassilis Papavassiliou], [[Stuart Russell]] ('''1999'''). ''Convergence of reinforcement learning with general function approximators.'' In Proc. IJCAI-99, Stockholm, [http://www.cs.berkeley.edu/~russell/papers/ijcai99-bridge.ps ps]
 
* [http://www.ilsp.gr/homepages/papavasiliou_eng.html Vassilis Papavassiliou], [[Stuart Russell]] ('''1999'''). ''Convergence of reinforcement learning with general function approximators.'' In Proc. IJCAI-99, Stockholm, [http://www.cs.berkeley.edu/~russell/papers/ijcai99-bridge.ps ps]
 
* [[Marco Wiering]] ('''1999'''). ''Explorations in Efficient Reinforcement Learning''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_Amsterdam University of Amsterdam], advisors [[Mathematician#FGroen|Frans Groen]] and [[Jürgen Schmidhuber]]
 
* [[Marco Wiering]] ('''1999'''). ''Explorations in Efficient Reinforcement Learning''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_Amsterdam University of Amsterdam], advisors [[Mathematician#FGroen|Frans Groen]] and [[Jürgen Schmidhuber]]
 +
* [[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 ...==
 
==2000 ...==
 
* [[Sebastian Thrun]], [[Michael L. Littman]] ('''2000'''). ''A Review of Reinforcement Learning''. [http://www.informatik.uni-trier.de/~ley/db/journals/aim/aim21.html#ThrunL00 AI Magazine, Vol. 21], No. 1
 
* [[Sebastian Thrun]], [[Michael L. Littman]] ('''2000'''). ''A Review of Reinforcement Learning''. [http://www.informatik.uni-trier.de/~ley/db/journals/aim/aim21.html#ThrunL00 AI Magazine, Vol. 21], No. 1
Line 73: Line 78:
 
* [[Andrew Ng]], [[Stuart Russell]] ('''2000'''). ''Algorithms for inverse reinforcement learning.'' In Proceedings of the Seventeenth International Conference on Machine Learning, Stanford, California: Morgan Kaufmann, [http://www.cs.berkeley.edu/~russell/papers/ml00-irl.pdf pdf]
 
* [[Andrew Ng]], [[Stuart Russell]] ('''2000'''). ''Algorithms for inverse reinforcement learning.'' In Proceedings of the Seventeenth International Conference on Machine Learning, Stanford, California: Morgan Kaufmann, [http://www.cs.berkeley.edu/~russell/papers/ml00-irl.pdf pdf]
 
* [http://www.cs.ou.edu/~hougen/ Dean F. Hougen], [http://www-users.cs.umn.edu/~gini/ Maria Gini], [[James R. Slagle]] ('''2000'''). ''[http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.23.2633 An Integrated Connectionist Approach to Reinforcement Learning for Robotic Control]''. ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
 
* [http://www.cs.ou.edu/~hougen/ Dean F. Hougen], [http://www-users.cs.umn.edu/~gini/ Maria Gini], [[James R. Slagle]] ('''2000'''). ''[http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.23.2633 An Integrated Connectionist Approach to Reinforcement Learning for Robotic Control]''. ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
* [[Jonathan Baxter]], [[Peter Bartlett]] ('''2000'''). ''Reinforcement Learning on POMDPs via Direct Gradient Ascent''. [http://dblp.uni-trier.de/db/conf/icml/icml2000.html ICML 2000], [https://pdfs.semanticscholar.org/b874/98f0879d312c308889135203b17069aa0486.pdf pdf]
+
* [[Jonathan Baxter]], [[Mathematician#PBartlett|Peter Bartlett]] ('''2000'''). ''Reinforcement Learning on POMDPs via Direct Gradient Ascent''. [http://dblp.uni-trier.de/db/conf/icml/icml2000.html ICML 2000], [https://pdfs.semanticscholar.org/b874/98f0879d312c308889135203b17069aa0486.pdf pdf]
 
* [[Doina Precup]] ('''2000'''). ''Temporal Abstraction in Reinforcement Learning''. Ph.D. Dissertation, Department of Computer Science, [https://en.wikipedia.org/wiki/University_of_Massachusetts_Amherst University of Massachusetts], [https://en.wikipedia.org/wiki/Amherst,_Massachusetts Amherst].
 
* [[Doina Precup]] ('''2000'''). ''Temporal Abstraction in Reinforcement Learning''. Ph.D. Dissertation, Department of Computer Science, [https://en.wikipedia.org/wiki/University_of_Massachusetts_Amherst University of Massachusetts], [https://en.wikipedia.org/wiki/Amherst,_Massachusetts Amherst].
 
* [[Robert Levinson]], [[Ryan Weber]] ('''2001'''). ''Chess Neighborhoods, Function Combinations and Reinforcements Learning''. In Computers and Games (eds. [[Tony Marsland]] and I. Frank). [https://en.wikipedia.org/wiki/Lecture_Notes_in_Computer_Science Lecture Notes in Computer Science],. Springer,. [http://users.soe.ucsc.edu/~levinson/Papers/CNFCRL.pdf pdf]
 
* [[Robert Levinson]], [[Ryan Weber]] ('''2001'''). ''Chess Neighborhoods, Function Combinations and Reinforcements Learning''. In Computers and Games (eds. [[Tony Marsland]] and I. Frank). [https://en.wikipedia.org/wiki/Lecture_Notes_in_Computer_Science Lecture Notes in Computer Science],. Springer,. [http://users.soe.ucsc.edu/~levinson/Papers/CNFCRL.pdf pdf]
 
* [[Marco Block-Berlitz]] ('''2003'''). ''Reinforcement Learning in der Schachprogrammierung''. Studienarbeit, Freie Universität Berlin, Dozent: [[Raúl Rojas|Prof. Dr. Raúl Rojas]], [http://page.mi.fu-berlin.de/block/Skripte/Reinforcement.pdf pdf] (German)
 
* [[Marco Block-Berlitz]] ('''2003'''). ''Reinforcement Learning in der Schachprogrammierung''. Studienarbeit, Freie Universität Berlin, Dozent: [[Raúl Rojas|Prof. Dr. Raúl Rojas]], [http://page.mi.fu-berlin.de/block/Skripte/Reinforcement.pdf pdf] (German)
* [[Henk Mannen]] ('''2003'''). ''Learning to play chess using reinforcement learning with database games''. Master’s thesis, [http://students.uu.nl/en/hum/cognitive-artificial-intelligence Cognitive Artificial Intelligence], [https://en.wikipedia.org/wiki/Utrecht_University Utrecht University]
+
* [[Henk Mannen]] ('''2003'''). ''Learning to play chess using reinforcement learning with database games''. Master’s thesis, Cognitive Artificial Intelligence, [https://en.wikipedia.org/wiki/Utrecht_University Utrecht University], [https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.109.810&rep=rep1&type=pdf pdf]
 
* [[Joelle Pineau]], [[Geoffrey Gordon]], [[Sebastian Thrun]] ('''2003'''). ''Point-based value iteration: An anytime algorithm for POMDPs''. [[Conferences#IJCAI2003|IJCAI]], [http://www.fore.robot.cc/papers/Pineau03a.pdf pdf]
 
* [[Joelle Pineau]], [[Geoffrey Gordon]], [[Sebastian Thrun]] ('''2003'''). ''Point-based value iteration: An anytime algorithm for POMDPs''. [[Conferences#IJCAI2003|IJCAI]], [http://www.fore.robot.cc/papers/Pineau03a.pdf pdf]
 +
* [https://dblp.uni-trier.de/pers/hd/k/Kerr:Amy_J= Amy J. Kerr], [[Todd W. Neller]], [https://dblp.uni-trier.de/pers/hd/p/Pilla:Christopher_J=_La Christopher J. La Pilla] , [https://dblp.uni-trier.de/pers/hd/s/Schompert:Michael_D= Michael D. Schompert] ('''2002'''). ''[https://www.semanticscholar.org/paper/Java-Resources-for-Teaching-Reinforcement-Learning-Kerr-Neller/3d84018eb8b8668c13d1d4f6efca4442af2915b4 Java Resources for Teaching Reinforcement Learning]''. [https://dblp.uni-trier.de/db/conf/pdpta/pdpta2003-3.html PDPTA 2003]
 
* [[Yngvi Björnsson]], Vignir Hafsteinsson, Ársæll Jóhannsson, Einar Jónsson ('''2004'''). ''Efficient Use of Reinforcement Learning in a Computer Game''. In Computer Games: Artificial Intellignece, Design and Education (CGAIDE'04), pp. 379–383, 2004. [http://www.ru.is/faculty/yngvi/pdf/BjornssonHJJ04.pdf pdf]
 
* [[Yngvi Björnsson]], Vignir Hafsteinsson, Ársæll Jóhannsson, Einar Jónsson ('''2004'''). ''Efficient Use of Reinforcement Learning in a Computer Game''. In Computer Games: Artificial Intellignece, Design and Education (CGAIDE'04), pp. 379–383, 2004. [http://www.ru.is/faculty/yngvi/pdf/BjornssonHJJ04.pdf pdf]
 
* [http://imranontech.com/ Imran Ghory] ('''2004'''). ''Reinforcement learning in board games''. CSTR-04-004, [http://www.cs.bris.ac.uk/ Department of Computer Science], [https://en.wikipedia.org/wiki/University_of_Bristol University of Bristol]. [http://www.cs.bris.ac.uk/Publications/Papers/2000100.pdf pdf] <ref>[http://www.cs.bris.ac.uk/Publications/pub_master.jsp?type=117 University of Bristol - Department of Computer Science - Technical Reports]</ref>
 
* [http://imranontech.com/ Imran Ghory] ('''2004'''). ''Reinforcement learning in board games''. CSTR-04-004, [http://www.cs.bris.ac.uk/ Department of Computer Science], [https://en.wikipedia.org/wiki/University_of_Bristol University of Bristol]. [http://www.cs.bris.ac.uk/Publications/Papers/2000100.pdf pdf] <ref>[http://www.cs.bris.ac.uk/Publications/pub_master.jsp?type=117 University of Bristol - Department of Computer Science - Technical Reports]</ref>
Line 91: Line 97:
 
* [[Marco Block-Berlitz|Marco Block]], Maro Bader, [http://page.mi.fu-berlin.de/tapia/ Ernesto Tapia], Marte Ramírez, Ketill Gunnarsson, Erik Cuevas, Daniel Zaldivar, [[Raúl Rojas]] ('''2008'''). ''Using Reinforcement Learning in Chess Engines''. CONCIBE SCIENCE 2008, [http://www.micai.org/rcs/ Research in Computing Science]: Special Issue in Electronics and Biomedical Engineering, Computer Science and Informatics, ISSN:1870-4069, Vol. 35, pp. 31-40, [https://en.wikipedia.org/wiki/Guadalajara Guadalajara], Mexico, [http://page.mi.fu-berlin.de/block/concibe2008.pdf pdf]
 
* [[Marco Block-Berlitz|Marco Block]], Maro Bader, [http://page.mi.fu-berlin.de/tapia/ Ernesto Tapia], Marte Ramírez, Ketill Gunnarsson, Erik Cuevas, Daniel Zaldivar, [[Raúl Rojas]] ('''2008'''). ''Using Reinforcement Learning in Chess Engines''. CONCIBE SCIENCE 2008, [http://www.micai.org/rcs/ Research in Computing Science]: Special Issue in Electronics and Biomedical Engineering, Computer Science and Informatics, ISSN:1870-4069, Vol. 35, pp. 31-40, [https://en.wikipedia.org/wiki/Guadalajara Guadalajara], Mexico, [http://page.mi.fu-berlin.de/block/concibe2008.pdf pdf]
 
* [[Cécile Germain-Renaud]], [[Julien Pérez]], [[Balázs Kégl]], [[Charles Loomis]] ('''2008'''). ''Grid Differentiated Services: a Reinforcement Learning Approach''. In 8th [[IEEE]] Symposium on Cluster Computing and the Grid. Lyon, [http://hal.inria.fr/docs/00/28/78/26/PDF/RLccg08.pdf pdf]
 
* [[Cécile Germain-Renaud]], [[Julien Pérez]], [[Balázs Kégl]], [[Charles Loomis]] ('''2008'''). ''Grid Differentiated Services: a Reinforcement Learning Approach''. In 8th [[IEEE]] Symposium on Cluster Computing and the Grid. Lyon, [http://hal.inria.fr/docs/00/28/78/26/PDF/RLccg08.pdf pdf]
 +
* [[Balázs Csanád Csáji]], [https://dblp.dagstuhl.de/pers/hd/m/Monostori:L=aacute=szl=oacute= László Monostori] ('''2008'''). ''Value function based reinforcement learning in changing Markovian environments''. [https://en.wikipedia.org/wiki/Journal_of_Machine_Learning_Research Journal of Machine Learning Research], Vol. 9, [http://www.jmlr.org/papers/volume9/csaji08a/csaji08a.pdf pdf]
 
* [[David Silver]] ('''2009'''). ''Reinforcement Learning and Simulation-Based Search''. Ph.D. thesis, [[University of Alberta]]. [http://webdocs.cs.ualberta.ca/~silver/David_Silver/Publications_files/thesis.pdf pdf]
 
* [[David Silver]] ('''2009'''). ''Reinforcement Learning and Simulation-Based Search''. Ph.D. thesis, [[University of Alberta]]. [http://webdocs.cs.ualberta.ca/~silver/David_Silver/Publications_files/thesis.pdf pdf]
 +
* [[Marcin Szubert]] ('''2009'''). ''Coevolutionary Reinforcement Learning and its Application to Othello''. M.Sc. thesis, [https://en.wikipedia.org/wiki/Pozna%C5%84_University_of_Technology Poznań University of Technology], supervisor [[Krzysztof Krawiec]], [https://mszubert.github.io/papers/Szubert_2009_MSC.pdf pdf]
 +
* [[Joelle Pineau]], [[Geoffrey Gordon]], [[Sebastian Thrun]] ('''2006, 2011'''). ''Anytime Point-Based Approximations for Large POMDPs''. [https://en.wikipedia.org/wiki/Journal_of_Artificial_Intelligence_Research Journal of Artificial Intelligence Research], Vol. 27, [https://arxiv.org/abs/1110.0027 arXiv:1110.0027]
 
==2010 ...==
 
==2010 ...==
 
* [[Joel Veness]], [[Kee Siong Ng]], [[Marcus Hutter]], [[David Silver]] ('''2010'''). ''Reinforcement Learning via AIXI Approximation''. Association for the Advancement of Artificial Intelligence (AAAI), [http://jveness.info/publications/veness_rl_via_aixi_approx.pdf pdf]
 
* [[Joel Veness]], [[Kee Siong Ng]], [[Marcus Hutter]], [[David Silver]] ('''2010'''). ''Reinforcement Learning via AIXI Approximation''. Association for the Advancement of Artificial Intelligence (AAAI), [http://jveness.info/publications/veness_rl_via_aixi_approx.pdf pdf]
 
* [[Julien Pérez]], [[Cécile Germain-Renaud]], [[Balázs Kégl]], [[Charles Loomis]] ('''2010'''). ''Multi-objective Reinforcement Learning for Responsive Grids''. In The Journal of Grid Computing. [http://hal.archives-ouvertes.fr/docs/00/49/15/60/PDF/RLGrid_JGC09_V7.pdf pdf]
 
* [[Julien Pérez]], [[Cécile Germain-Renaud]], [[Balázs Kégl]], [[Charles Loomis]] ('''2010'''). ''Multi-objective Reinforcement Learning for Responsive Grids''. In The Journal of Grid Computing. [http://hal.archives-ouvertes.fr/docs/00/49/15/60/PDF/RLGrid_JGC09_V7.pdf pdf]
 
* [[Csaba Szepesvári]] ('''2010'''). ''[https://sites.ualberta.ca/~szepesva/RLBook.html Algorithms for Reinforcement Learning]''. Morgan & Claypool
 
* [[Csaba Szepesvári]] ('''2010'''). ''[https://sites.ualberta.ca/~szepesva/RLBook.html Algorithms for Reinforcement Learning]''. Morgan & Claypool
 +
* [https://dblp.org/pers/hd/z/Zaragoza:Julio_H= Julio H. Zaragoza], [[Eduardo F. Morales]] ('''2010'''). ''Relational Reinforcement Learning with Continuous Actions by Combining Behavioral Cloning and Locally Weighted Regression''. Journal of Intelligent Systems and Applications, Vol. 2
 
'''2011'''
 
'''2011'''
 
* [[Peter Auer]] ('''2011'''). ''Exploration and Exploitation in Online Learning''. [http://dblp.uni-trier.de/db/conf/icais/icais2011.html#Auer11 ICAIS 2011]
 
* [[Peter Auer]] ('''2011'''). ''Exploration and Exploitation in Online Learning''. [http://dblp.uni-trier.de/db/conf/icais/icais2011.html#Auer11 ICAIS 2011]
Line 103: Line 113:
 
: [[István Szita]] ('''2012'''). ''[http://link.springer.com/chapter/10.1007%2F978-3-642-27645-3_17 Reinforcement Learning in Games]''. Chapter 17
 
: [[István Szita]] ('''2012'''). ''[http://link.springer.com/chapter/10.1007%2F978-3-642-27645-3_17 Reinforcement Learning in Games]''. Chapter 17
 
* [[Thomas J. Walsh]], [[István Szita]], [[Carlos Diuk]], [[Michael L. Littman]] ('''2012'''). ''Exploring compact reinforcement-learning representations with linear regression''. [https://arxiv.org/abs/1205.2606 arXiv:1205.2606]
 
* [[Thomas J. Walsh]], [[István Szita]], [[Carlos Diuk]], [[Michael L. Littman]] ('''2012'''). ''Exploring compact reinforcement-learning representations with linear regression''. [https://arxiv.org/abs/1205.2606 arXiv:1205.2606]
* [[Arthur Guez]], [[David Silver]], [[Peter Dayan]] ('''2012'''). ''Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search''. [http://papers.nips.cc/book/advances-in-neural-information-processing-systems-25-2012 NIPS 2012], [https://papers.nips.cc/paper/4767-efficient-bayes-adaptive-reinforcement-learning-using-sample-based-search.pdf pdf]
+
* [[Arthur Guez]], [[David Silver]], [[Peter Dayan]] ('''2012'''). ''[https://papers.nips.cc/paper/4767-efficient-bayes-adaptive-reinforcement-learning-using-sample-based-search Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search]''. [https://papers.nips.cc/book/advances-in-neural-information-processing-systems-25-2012 NIPS 2012]
 
'''2013'''
 
'''2013'''
 
* [[Arthur Guez]], [[David Silver]], [[Peter Dayan]] ('''2013'''). ''Scalable and Efficient Bayes-Adaptive Reinforcement Learning Based on Monte-Carlo Tree Search''. [https://en.wikipedia.org/wiki/Journal_of_Artificial_Intelligence_Research Journal of Artificial Intelligence Research], Vol. 48, [https://www.jair.org/media/4117/live-4117-7507-jair.pdf pdf]
 
* [[Arthur Guez]], [[David Silver]], [[Peter Dayan]] ('''2013'''). ''Scalable and Efficient Bayes-Adaptive Reinforcement Learning Based on Monte-Carlo Tree Search''. [https://en.wikipedia.org/wiki/Journal_of_Artificial_Intelligence_Research Journal of Artificial Intelligence Research], Vol. 48, [https://www.jair.org/media/4117/live-4117-7507-jair.pdf pdf]
Line 114: Line 124:
 
* [[Marcin Szubert]] ('''2014'''). ''Coevolutionary Shaping for Reinforcement Learning''. Ph.D. thesis, [https://en.wikipedia.org/wiki/Pozna%C5%84_University_of_Technology Poznań University of Technology], supervisor [[Krzysztof Krawiec]], co-supervisor [[Wojciech Jaśkowski]], [http://www.cs.put.poznan.pl/mszubert/pub/phdthesis.pdf pdf]
 
* [[Marcin Szubert]] ('''2014'''). ''Coevolutionary Shaping for Reinforcement Learning''. Ph.D. thesis, [https://en.wikipedia.org/wiki/Pozna%C5%84_University_of_Technology Poznań University of Technology], supervisor [[Krzysztof Krawiec]], co-supervisor [[Wojciech Jaśkowski]], [http://www.cs.put.poznan.pl/mszubert/pub/phdthesis.pdf pdf]
 
==2015 ...==
 
==2015 ...==
* [[Volodymyr Mnih]], [[Koray Kavukcuoglu]], [[David Silver]], [[Andrei A. Rusu]], [[Joel Veness]], [[Marc G. Bellemare]], [[Alex Graves]], [[Martin Riedmiller]], [[Andreas K. Fidjeland]], [[Georg Ostrovski]], [[Stig Petersen]], [[Charles Beattie]], [[Amir Sadik]], [[Ioannis Antonoglou]], [[Helen King]], [[Dharshan Kumaran]], [[Daan Wierstra]], [[Shane Legg]], [[Demis Hassabis]] ('''2015'''). ''[http://www.nature.com/nature/journal/v518/n7540/abs/nature14236.html Human-level control through deep reinforcement learning]''. [https://en.wikipedia.org/wiki/Nature_%28journal%29 Nature], Vol. 518
+
* [[Volodymyr Mnih]], [[Koray Kavukcuoglu]], [[David Silver]], [[Mathematician#AARusu|Andrei A. Rusu]], [[Joel Veness]], [[Marc G. Bellemare]], [[Alex Graves]], [[Martin Riedmiller]], [[Andreas K. Fidjeland]], [[Georg Ostrovski]], [[Stig Petersen]], [[Charles Beattie]], [[Amir Sadik]], [[Ioannis Antonoglou]], [[Helen King]], [[Dharshan Kumaran]], [[Daan Wierstra]], [[Shane Legg]], [[Demis Hassabis]] ('''2015'''). ''[http://www.nature.com/nature/journal/v518/n7540/abs/nature14236.html Human-level control through deep reinforcement learning]''. [https://en.wikipedia.org/wiki/Nature_%28journal%29 Nature], Vol. 518
 
* [[Tobias Graf]], [[Marco Platzner]] ('''2015'''). ''Adaptive Playouts in Monte Carlo Tree Search with Policy Gradient Reinforcement Learning''. [[Advances in Computer Games 14]]
 
* [[Tobias Graf]], [[Marco Platzner]] ('''2015'''). ''Adaptive Playouts in Monte Carlo Tree Search with Policy Gradient Reinforcement Learning''. [[Advances in Computer Games 14]]
 
* [[Arun Nair]], [[Praveen Srinivasan]], [[Sam Blackwell]], [[Cagdas Alcicek]], [[Rory Fearon]], [[Alessandro De Maria]], [[Veda Panneershelvam]], [[Mustafa Suleyman]], [[Charles Beattie]], [[Stig Petersen]], [[Shane Legg]], [[Volodymyr Mnih]], [[Koray Kavukcuoglu]], [[David Silver]] ('''2015'''). ''Massively Parallel Methods for Deep Reinforcement Learning''. [http://arxiv.org/abs/1507.04296 arXiv:1507.04296]
 
* [[Arun Nair]], [[Praveen Srinivasan]], [[Sam Blackwell]], [[Cagdas Alcicek]], [[Rory Fearon]], [[Alessandro De Maria]], [[Veda Panneershelvam]], [[Mustafa Suleyman]], [[Charles Beattie]], [[Stig Petersen]], [[Shane Legg]], [[Volodymyr Mnih]], [[Koray Kavukcuoglu]], [[David Silver]] ('''2015'''). ''Massively Parallel Methods for Deep Reinforcement Learning''. [http://arxiv.org/abs/1507.04296 arXiv:1507.04296]
Line 132: Line 142:
 
* [[Marc Lanctot]], [[Vinícius Flores Zambaldi]], [[Audrunas Gruslys]], [[Angeliki Lazaridou]], [[Karl Tuyls]], [[Julien Pérolat]], [[David Silver]], [[Thore Graepel]] ('''2017'''). ''A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning''. [https://arxiv.org/abs/1711.00832 arXiv:1711.00832]
 
* [[Marc Lanctot]], [[Vinícius Flores Zambaldi]], [[Audrunas Gruslys]], [[Angeliki Lazaridou]], [[Karl Tuyls]], [[Julien Pérolat]], [[David Silver]], [[Thore Graepel]] ('''2017'''). ''A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning''. [https://arxiv.org/abs/1711.00832 arXiv:1711.00832]
 
* [[David Silver]], [[Julian Schrittwieser]], [[Karen Simonyan]], [[Ioannis Antonoglou]], [[Shih-Chieh Huang|Aja Huang]], [[Arthur Guez]], [[Thomas Hubert]], [[Lucas Baker]], [[Matthew Lai]], [[Adrian Bolton]], [[Yutian Chen]], [[Timothy Lillicrap]], [[Fan Hui]], [[Laurent Sifre]], [[George van den Driessche]], [[Thore Graepel]], [[Demis Hassabis]] ('''2017'''). ''[https://www.nature.com/nature/journal/v550/n7676/full/nature24270.html Mastering the game of Go without human knowledge]''. [https://en.wikipedia.org/wiki/Nature_%28journal%29 Nature], Vol. 550,  [https://www.gwern.net/docs/rl/2017-silver.pdf pdf] <ref>[https://deepmind.com/blog/alphago-zero-learning-scratch/ AlphaGo Zero: Learning from scratch] by [[Demis Hassabis]] and [[David Silver]], [[DeepMind]], October 18, 2017</ref>
 
* [[David Silver]], [[Julian Schrittwieser]], [[Karen Simonyan]], [[Ioannis Antonoglou]], [[Shih-Chieh Huang|Aja Huang]], [[Arthur Guez]], [[Thomas Hubert]], [[Lucas Baker]], [[Matthew Lai]], [[Adrian Bolton]], [[Yutian Chen]], [[Timothy Lillicrap]], [[Fan Hui]], [[Laurent Sifre]], [[George van den Driessche]], [[Thore Graepel]], [[Demis Hassabis]] ('''2017'''). ''[https://www.nature.com/nature/journal/v550/n7676/full/nature24270.html Mastering the game of Go without human knowledge]''. [https://en.wikipedia.org/wiki/Nature_%28journal%29 Nature], Vol. 550,  [https://www.gwern.net/docs/rl/2017-silver.pdf pdf] <ref>[https://deepmind.com/blog/alphago-zero-learning-scratch/ AlphaGo Zero: Learning from scratch] by [[Demis Hassabis]] and [[David Silver]], [[DeepMind]], October 18, 2017</ref>
* [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=tiE4g64AAAAJ&hl=en Maithra Raghu], [https://scholar.google.com/citations?user=ZZNxNAYAAAAJ&hl=en Alex Irpan], [[Mathematician#JAndreas|Jacob Andreas]], [[Mathematician#RKleinberg|Robert Kleinberg]], [[Quoc V. Le]], [[Jon Kleinberg]] ('''2017'''). ''Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?'' [https://arxiv.org/abs/1711.02301 arXiv:1711.02301]
 +
 
 
* [[David Silver]], [[Thomas Hubert]], [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Matthew Lai]], [[Arthur Guez]], [[Marc Lanctot]], [[Laurent Sifre]], [[Dharshan Kumaran]], [[Thore Graepel]], [[Timothy Lillicrap]], [[Karen Simonyan]], [[Demis Hassabis]] ('''2017'''). ''Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm''. [https://arxiv.org/abs/1712.01815 arXiv:1712.01815] » [[AlphaZero]]
 
* [[David Silver]], [[Thomas Hubert]], [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Matthew Lai]], [[Arthur Guez]], [[Marc Lanctot]], [[Laurent Sifre]], [[Dharshan Kumaran]], [[Thore Graepel]], [[Timothy Lillicrap]], [[Karen Simonyan]], [[Demis Hassabis]] ('''2017'''). ''Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm''. [https://arxiv.org/abs/1712.01815 arXiv:1712.01815] » [[AlphaZero]]
* [[Kei Takada]], [[Hiroyuki Iizuka]], [[Masahito Yamamoto]] ('''2017'''). ''Reinforcement Learning for Creating Evaluation Function Using Convolutional Neural Network in Hex''. TAAI 2017 » [[Hex]], [[Neural Networks#Convolutional|CNN]]
+
* [[Kei Takada]], [[Hiroyuki Iizuka]], [[Masahito Yamamoto]] ('''2017'''). ''Reinforcement Learning for Creating Evaluation Function Using Convolutional Neural Network in Hex''. [[TAAI 2017]] » [[Hex]], [[Neural Networks#Convolutional|CNN]]
 
* [[Ari Weinstein]], [[Matthew Botvinick]] ('''2017'''). ''Structure Learning in Motor Control: A Deep Reinforcement Learning Model''. [https://arxiv.org/abs/1706.06827 arXiv:1706.06827]
 
* [[Ari Weinstein]], [[Matthew Botvinick]] ('''2017'''). ''Structure Learning in Motor Control: A Deep Reinforcement Learning Model''. [https://arxiv.org/abs/1706.06827 arXiv:1706.06827]
 +
* [[Takuya Hiraoka]], [https://dblp.org/pers/hd/t/Tsuchida:Masaaki Masaaki Tsuchida], [https://dblp.org/pers/hd/w/Watanabe:Yotaro Yotaro Watanabe] ('''2017'''). ''Deep Reinforcement Learning for Inquiry Dialog Policies with Logical Formula Embeddings''. [https://arxiv.org/abs/1708.00667 arXiv:1708.00667]
 
* [[William Uther]] ('''2017'''). ''[https://link.springer.com/referenceworkentry/10.1007/978-1-4899-7687-1_512 Markov Decision Processes]''. in [https://en.wikipedia.org/wiki/Claude_Sammut Claude Sammut], [https://en.wikipedia.org/wiki/Geoff_Webb Geoffrey I. Webb] (eds) ('''2017'''). ''[https://link.springer.com/referencework/10.1007%2F978-1-4899-7687-1 Encyclopedia of Machine Learning and Data Mining]''. [https://en.wikipedia.org/wiki/Springer_Science%2BBusiness_Media Springer]
 
* [[William Uther]] ('''2017'''). ''[https://link.springer.com/referenceworkentry/10.1007/978-1-4899-7687-1_512 Markov Decision Processes]''. in [https://en.wikipedia.org/wiki/Claude_Sammut Claude Sammut], [https://en.wikipedia.org/wiki/Geoff_Webb Geoffrey I. Webb] (eds) ('''2017'''). ''[https://link.springer.com/referencework/10.1007%2F978-1-4899-7687-1 Encyclopedia of Machine Learning and Data Mining]''. [https://en.wikipedia.org/wiki/Springer_Science%2BBusiness_Media Springer]
 +
* [https://scholar.google.com/citations?user=zLksndkAAAAJ&hl=en Jayvant Anantpur], [https://dblp.org/pid/09/10702.html Nagendra Gulur Dwarakanath], [https://dblp.org/pid/16/4410.html Shivaram Kalyanakrishnan], [[Shalabh Bhatnagar]], [https://dblp.org/pid/45/3592.html R. Govindarajan] ('''2017'''). ''RLWS: A Reinforcement Learning based GPU Warp Scheduler''. [https://arxiv.org/abs/1712.04303 arXiv:1712.04303]
 
'''2018'''
 
'''2018'''
 +
* [[Hui Wang]], [[Michael Emmerich]], [[Aske Plaat]] ('''2018'''). ''Monte Carlo Q-learning for General Game Playing''. [https://arxiv.org/abs/1802.05944 arXiv:1802.05944] » [[Monte-Carlo Tree Search|MCTS]], [[General Game Playing]]
 +
* [[Hui Wang]], [[Michael Emmerich]], [[Aske Plaat]] ('''2018'''). ''Assessing the Potential of Classical Q-learning in General Game Playing''. [https://arxiv.org/abs/1810.06078 arXiv:1810.06078]
 +
* [https://scholar.google.com/citations?user=n12uNYcAAAAJ&hl=en Vincent Francois-Lavet], [https://scholar.google.com/citations?user=dy_JBs0AAAAJ&hl=en Peter Henderson], [https://scholar.google.ca/citations?user=2_4Rs44AAAAJ&hl=en Riashat Islam], [https://scholar.google.com/citations?user=uyYPun0AAAAJ&hl=en Marc G. Bellemare], [[Joelle Pineau]] ('''2018'''). ''An Introduction to Deep Reinforcement Learning''. [https://arxiv.org/abs/1811.12560 arXiv:1811.12560]
 
* [[David Silver]], [[Thomas Hubert]], [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Matthew Lai]], [[Arthur Guez]], [[Marc Lanctot]], [[Laurent Sifre]], [[Dharshan Kumaran]], [[Thore Graepel]], [[Timothy Lillicrap]], [[Karen Simonyan]], [[Demis Hassabis]] ('''2018'''). ''[http://science.sciencemag.org/content/362/6419/1140 A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play]''. [https://en.wikipedia.org/wiki/Science_(journal) Science], Vol. 362, No. 6419 <ref>[https://deepmind.com/blog/alphazero-shedding-new-light-grand-games-chess-shogi-and-go/ AlphaZero: Shedding new light on the grand games of chess, shogi and Go] by [[David Silver]], [[Thomas Hubert]], [[Julian Schrittwieser]] and [[Demis Hassabis]], [[DeepMind]], December 03, 2018</ref>
 
* [[David Silver]], [[Thomas Hubert]], [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Matthew Lai]], [[Arthur Guez]], [[Marc Lanctot]], [[Laurent Sifre]], [[Dharshan Kumaran]], [[Thore Graepel]], [[Timothy Lillicrap]], [[Karen Simonyan]], [[Demis Hassabis]] ('''2018'''). ''[http://science.sciencemag.org/content/362/6419/1140 A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play]''. [https://en.wikipedia.org/wiki/Science_(journal) Science], Vol. 362, No. 6419 <ref>[https://deepmind.com/blog/alphazero-shedding-new-light-grand-games-chess-shogi-and-go/ AlphaZero: Shedding new light on the grand games of chess, shogi and Go] by [[David Silver]], [[Thomas Hubert]], [[Julian Schrittwieser]] and [[Demis Hassabis]], [[DeepMind]], December 03, 2018</ref>
 +
* [[Tianhe Wang]], [[Tomoyuki Kaneko]] ('''2018'''). ''Application of Deep Reinforcement Learning in Werewolf Game Agents''. [[TAAI 2018]]
 +
* [[Taichi Nakayashiki]], [[Tomoyuki Kaneko]] ('''2018'''). ''Learning of Evaluation Functions via Self-Play Enhanced by Checkmate Search''. [[TAAI 2018]]
 +
* [[Hung Guei]], [[Ting-Han Wei]], [[I-Chen Wu]] ('''2018'''). ''Using 2048-like games as a pedagogical tool for reinforcement learning''. [[CG 2018]], [[ICGA Journal#40_3|ICGA Journal, Vol. 40, No. 3]]
 +
'''2019'''
 +
* [https://scholar.google.co.uk/citations?user=OAkRr-YAAAAJ&hl=en Sanjeevan Ahilan], [[Peter Dayan]] ('''2019'''). ''Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning''. [https://arxiv.org/abs/1901.08492 arXiv:1901.08492]
 +
* [https://scholar.google.co.in/citations?user=1QlrvHkAAAAJ&hl=en Chandramouli Kamanchi], [https://scholar.google.co.in/citations?user=nx4NlpsAAAAJ&hl=en Raghuram Bharadwaj Diddigi], [[Shalabh Bhatnagar]] ('''2019'''). ''Successive Over Relaxation Q-Learning''. [https://arxiv.org/abs/1903.03812 arXiv:1903.03812]
 +
* [https://scholar.google.co.in/citations?user=1QlrvHkAAAAJ&hl=en Chandramouli Kamanchi], [https://scholar.google.co.in/citations?user=nx4NlpsAAAAJ&hl=en Raghuram Bharadwaj Diddigi], [[Shalabh Bhatnagar]] ('''2019'''). ''Second Order Value Iteration in Reinforcement Learning''. [https://arxiv.org/abs/1905.03927 arXiv:1905.03927]
 +
* [[Marc Lanctot]], [[Edward Lockhart]], [[Jean-Baptiste Lespiau]], [[Vinicius Zambaldi]], [[Satyaki Upadhyay]], [[Julien Pérolat]], [[Sriram Srinivasan]], [[Finbarr Timbers]], [[Karl Tuyls]], [[Shayegan Omidshafiei]], [[Daniel Hennes]], [[Dustin Morrill]], [[Paul Muller]], [[Timo Ewalds]], [[Ryan Faulkner]], [[János Kramár]], [[Bart De Vylder]], [[Brennan Saeta]], [[James Bradbury]], [[David Ding]], [[Sebastian Borgeaud]], [[Matthew Lai]], [[Julian Schrittwieser]], [[Thomas Anthony]], [[Edward Hughes]], [[Ivo Danihelka]], [[Jonah Ryan-Davis]] ('''2019'''). ''OpenSpiel: A Framework for Reinforcement Learning in Games''. [https://arxiv.org/abs/1908.09453 arXiv:1908.09453] <ref>[https://github.com/deepmind/open_spiel/blob/master/docs/contributing.md open_spiel/contributing.md at master · deepmind/open_spiel · GitHub]</ref>
 +
* [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Thomas Hubert]], [[Karen Simonyan]], [[Laurent Sifre]], [[Simon Schmitt]], [[Arthur Guez]], [[Edward Lockhart]], [[Demis Hassabis]], [[Thore Graepel]], [[Timothy Lillicrap]], [[David Silver]] ('''2019'''). ''Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model''. [https://arxiv.org/abs/1911.08265 arXiv:1911.08265] <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=72381 New DeepMind paper] by GregNeto, [[CCC]], November 21, 2019</ref>
 +
* [[Mathematician#SrbhBose|Sourabh Bose]] ('''2019'''). ''[https://rc.library.uta.edu/uta-ir/handle/10106/28094 Learning Representations Using Reinforcement Learning]''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_Texas_at_Arlington University of Texas at Arlington], advisor [[Mathematician#MHuber|Manfred Huber]] <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=7&t=72810&start=6 e: Board adaptive / tuning evaluation function - no NN/AI] by Tony P., [[CCC]], January 15, 2020</ref>
 +
==2020 ...==
 +
* [[Hung Guei]], [[Ting-Han Wei]], [[I-Chen Wu]] ('''2020'''). ''2048-like games for teaching reinforcement learning''. [[ICGA Journal#42_1|ICGA Journal, Vol. 42, No. 1]]
 +
* [https://dblp.org/pid/233/8144.html Indu John], [https://scholar.google.co.in/citations?user=1QlrvHkAAAAJ&hl=en Chandramouli Kamanchi], [[Shalabh Bhatnagar]] ('''2020'''). ''Generalized Speedy Q-Learning''. [[IEEE#CSL|IEEE Control Systems Letters]], Vol. 4, No. 3, [https://arxiv.org/abs/1911.00397 arXiv:1911.00397]
 +
* [[Takuya Hiraoka]], [https://dblp.org/pers/hd/i/Imagawa:Takahisa Takahisa Imagawa], [https://dblp.org/pers/hd/t/Tangkaratt:Voot Voot Tangkaratt], [https://dblp.org/pers/hd/o/Osa:Takayuki Takayuki Osa], [https://dblp.org/pers/hd/o/Onishi:Takashi Takashi Onishi], [https://dblp.org/pers/hd/t/Tsuruoka:Yoshimasa Yoshimasa Tsuruoka]  ('''2020'''). ''Meta-Model-Based Meta-Policy Optimization''. [https://arxiv.org/abs/2006.02608 arXiv:2006.02608]
 +
* [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Thomas Hubert]], [[Karen Simonyan]], [[Laurent Sifre]], [[Simon Schmitt]], [[Arthur Guez]], [[Edward Lockhar]], [[Demis Hassabis]], [[Thore Graepel]], [[Timothy Lillicrap]], [[David Silver]] ('''2020'''). ''[https://www.nature.com/articles/s41586-020-03051-4 Mastering Atari, Go, chess and shogi by planning with a learned model]''. [https://en.wikipedia.org/wiki/Nature_%28journal%29 Nature], Vol. 588 <ref>[https://deepmind.com/blog/article/muzero-mastering-go-chess-shogi-and-atari-without-rules?fbclid=IwAR3mSwrn1YXDKr9uuGm2GlFKh76wBilex7f8QvBiQecwiVmAvD6Bkyjx-rE MuZero: Mastering Go, chess, shogi and Atari without rules]</ref>
 +
* [[Tristan Cazenave]], [[Yen-Chi Chen]], [[Guan-Wei Chen]], [[Shi-Yu Chen]], [[Xian-Dong Chiu]], [[Julien Dehos]], [[Maria Elsa]], [[Qucheng Gong]], [[Hengyuan Hu]], [[Vasil Khalidov]], [[Cheng-Ling Li]], [[Hsin-I Lin]], [[Yu-Jin Lin]], [[Xavier Martinet]], [[Vegard Mella]], [[Jeremy Rapin]], [[Baptiste Roziere]], [[Gabriel Synnaeve]], [[Fabien Teytaud]], [[Olivier Teytaud]], [[Shi-Cheng Ye]], [[Yi-Jun Ye]], [[Shi-Jim Yen]], [[Sergey Zagoruyko]] ('''2020''').  ''Polygames: Improved zero learning''. [[ICGA Journal#42_4|ICGA Journal, Vol. 42, No. 4]], [https://arxiv.org/abs/2001.09832 arXiv:2001.09832], [https://arxiv.org/abs/2001.09832 arXiv:2001.09832]
  
 
=Postings=
 
=Postings=
 +
==1995 ...==
 
* [https://www.stmintz.com/ccc/index.php?id=28584 Parameter Tuning] by [[Jonathan Baxter]], [[CCC]], October 01, 1998 » [[KnightCap]]
 
* [https://www.stmintz.com/ccc/index.php?id=28584 Parameter Tuning] by [[Jonathan Baxter]], [[CCC]], October 01, 1998 » [[KnightCap]]
 +
: [https://www.stmintz.com/ccc/index.php?id=28819 Re: Parameter Tuning] by [[Don Beal]], [[CCC]], October 02, 1998
 +
==2000 ...==
 +
* [https://www.stmintz.com/ccc/index.php?id=117970 Pseudo-code for TD learning] by [[Daniel Homan]], [[CCC]], July 06, 2000 » [[Temporal Difference Learning]]
 
* [https://www.stmintz.com/ccc/index.php?id=147377 any good experiences with genetic algos or temporal difference learning?] by [[Rafael B. Andrist]], [[CCC]], January 01, 2001
 
* [https://www.stmintz.com/ccc/index.php?id=147377 any good experiences with genetic algos or temporal difference learning?] by [[Rafael B. Andrist]], [[CCC]], January 01, 2001
 +
* [https://www.stmintz.com/ccc/index.php?id=401974 Temporal Differences] by [[Peter Fendrich]], [[CCC]], December 21, 2004
 +
==2010 ...==
 
* [http://talkchess.com/forum/viewtopic.php?t=56913 *First release* Giraffe, a new engine based on deep learning] by [[Matthew Lai]], [[CCC]], July 08, 2015 » [[Deep Learning]], [[Giraffe]]
 
* [http://talkchess.com/forum/viewtopic.php?t=56913 *First release* Giraffe, a new engine based on deep learning] by [[Matthew Lai]], [[CCC]], July 08, 2015 » [[Deep Learning]], [[Giraffe]]
 
* [http://www.nervanasys.com/demystifying-deep-reinforcement-learning/ Demystifying Deep Reinforcement Learning] by [http://www.nervanasys.com/author/tambet/ Tambet Matiisen], [http://www.nervanasys.com/ Nervana], December 22, 2015
 
* [http://www.nervanasys.com/demystifying-deep-reinforcement-learning/ Demystifying Deep Reinforcement Learning] by [http://www.nervanasys.com/author/tambet/ Tambet Matiisen], [http://www.nervanasys.com/ Nervana], December 22, 2015
Line 148: Line 187:
 
* [http://www.talkchess.com/forum/viewtopic.php?t=65909 Google's AlphaGo team has been working on chess] by [[Peter Kappler]], [[CCC]], December 06, 2017 » [[AlphaZero]]
 
* [http://www.talkchess.com/forum/viewtopic.php?t=65909 Google's AlphaGo team has been working on chess] by [[Peter Kappler]], [[CCC]], December 06, 2017 » [[AlphaZero]]
 
* [http://www.talkchess.com/forum/viewtopic.php?t=65990 Understanding the power of reinforcement learning] by [[Michael Sherwin]], [[CCC]], December 12, 2017
 
* [http://www.talkchess.com/forum/viewtopic.php?t=65990 Understanding the power of reinforcement learning] by [[Michael Sherwin]], [[CCC]], December 12, 2017
 +
==2020 ...==
 +
* [http://www.talkchess.com/forum3/viewtopic.php?f=7&t=72810 Board adaptive / tuning evaluation function - no NN/AI] by Moritz Gedig, [[CCC]], January 14, 2020
 +
* [http://www.talkchess.com/forum3/viewtopic.php?f=7&t=75411 Unsupervised reinforcement tuning from zero] by Madeleine Birchfield, [[CCC]], October 16, 2020 » [[Automated Tuning]]
 +
* [http://www.talkchess.com/forum3/viewtopic.php?f=2&t=75606 Transhuman Chess with NN and RL...] by [[Srdja Matovic]], [[CCC]], October 30, 2020 » [[Neural Networks|NN]]
 +
* [http://www.talkchess.com/forum3/viewtopic.php?f=7&t=76465 Reinforcement learning project] by [[Harm Geert Muller]], [[CCC]], January 31, 2021 » [[Texel's Tuning Method]]
  
 
=External Links=  
 
=External Links=  
Line 180: Line 224:
 
* [http://videolectures.net/deeplearning2016_pineau_reinforcement_learning/ Introduction to Reinforcement Learning] by [[Joelle Pineau]], [[McGill University]], 2016, [https://en.wikipedia.org/wiki/YouTube YouTube] Video
 
* [http://videolectures.net/deeplearning2016_pineau_reinforcement_learning/ Introduction to Reinforcement Learning] by [[Joelle Pineau]], [[McGill University]], 2016, [https://en.wikipedia.org/wiki/YouTube YouTube] Video
 
: {{#evu:https://www.youtube.com/watch?v=O_1Z63EDMvQ|alignment=left|valignment=top}}
 
: {{#evu:https://www.youtube.com/watch?v=O_1Z63EDMvQ|alignment=left|valignment=top}}
 +
==OpenSpiel==
 +
* [https://github.com/deepmind/open_spiel GitHub - deepmind/open_spiel: OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games] <ref>[[Marc Lanctot]], [[Edward Lockhart]], [[Jean-Baptiste Lespiau]], [[Vinicius Zambaldi]], [[Satyaki Upadhyay]], [[Julien Pérolat]], [[Sriram Srinivasan]], [[Finbarr Timbers]], [[Karl Tuyls]], [[Shayegan Omidshafiei]], [[Daniel Hennes]], [[Dustin Morrill]], [[Paul Muller]], [[Timo Ewalds]], [[Ryan Faulkner]], [[János Kramár]], [[Bart De Vylder]], [[Brennan Saeta]], [[James Bradbury]], [[David Ding]], [[Sebastian Borgeaud]], [[Matthew Lai]], [[Julian Schrittwieser]], [[Thomas Anthony]], [[Edward Hughes]], [[Ivo Danihelka]], [[Jonah Ryan-Davis]] ('''2019'''). ''OpenSpiel: A Framework for Reinforcement Learning in Games''. [https://arxiv.org/abs/1908.09453 arXiv:1908.09453]</ref>
 +
** [https://github.com/deepmind/open_spiel/tree/master/open_spiel/algorithms open_spiel/open_spiel/algorithms at master · deepmind/open_spiel · GitHub]
 +
*** [https://github.com/deepmind/open_spiel/tree/master/open_spiel/algorithms/alpha_zero open_spiel/open_spiel/algorithms/alpha_zero at master · deepmind/open_spiel · GitHub]
 +
** [https://github.com/deepmind/open_spiel/tree/master/open_spiel/games open_spiel/open_spiel/games at master · deepmind/open_spiel · GitHub]
 +
*** [https://github.com/deepmind/open_spiel/tree/master/open_spiel/games/chess open_spiel/open_spiel/games/chess at master · deepmind/open_spiel · GitHub]
  
 
=References=  
 
=References=  
 
<references />
 
<references />
 
 
'''[[Learning|Up one Level]]'''
 
'''[[Learning|Up one Level]]'''
 +
[[Category:Videos]]

Revision as of 08:46, 15 April 2021

Home * Learning * Reinforcement Learning

Reinforcement Learning,
a learning paradigm inspired by behaviourist psychology and classical conditioning - learning by trial and error, interacting with an environment to map situations to actions in such a way that some notion of cumulative reward is maximized. In computer games, reinforcement learning deals with adjusting feature weights based on results or their subsequent predictions during self play.

Reinforcement learning is indebted to the idea of Markov decision processes (MDPs) in the field of optimal control utilizing dynamic programming techniques. The crucial exploitation and exploration tradeoff in multi-armed bandit problems as also considered in UCT of Monte-Carlo Tree Search - between "exploitation" of the machine that has the highest expected payoff and "exploration" to get more information about the expected payoffs of the other machines - is also faced in reinforcement learning.

Q-Learning

Q-Learning, introduced by Chris Watkins in 1989, is a simple way for agents to learn how to act optimally in controlled Markovian domains [2]. It amounts to an incremental method for dynamic programming which imposes limited computational demands. It works by successively improving its evaluations of the quality of particular actions at particular states. Q-learning converges to the optimum action-values with probability 1 so long as all actions are repeatedly sampled in all states and the action-values are represented discretely [3]. Q-learning has been successfully applied to deep learning by a Google DeepMind team in playing some Atari 2600 games as published in Nature, 2015, dubbed deep reinforcement learning or deep Q-networks [4], soon followed by the spectacular AlphaGo and AlphaZero breakthroughs.

Temporal Difference Learning

see main page Temporal Difference Learning

Q-learning at its simplest uses tables to store data. This very quickly loses viability with increasing sizes of state/action space of the system it is monitoring/controlling. One solution to this problem is to use an (adapted) artificial neural network as a function approximator, as demonstrated by Gerald Tesauro in his Backgammon playing temporal difference learning research [5] [6].

Temporal Difference Learning is a prediction method primarily used for reinforcement learning. In the domain of computer games and computer chess, TD learning is applied through self play, subsequently predicting the probability of winning a game during the sequence of moves from the initial position until the end, to adjust weights for a more reliable prediction.

See also

UCT

Selected Publications

1954 ...

1960 ...

1970 ...

1980 ...

1990 ...

1995 ...

2000 ...

2005 ...

2010 ...

2011

2012

István Szita (2012). Reinforcement Learning in Games. Chapter 17

2013

2014

2015 ...

2016

2017

2018

2019

2020 ...

Postings

1995 ...

Re: Parameter Tuning by Don Beal, CCC, October 02, 1998

2000 ...

2010 ...

2020 ...

External Links

Reinforcement Learning

MDP

Q-Learning

Courses

  1. Lecture 1: Introduction to Reinforcement Learning
  2. Lecture 2: Markov Decision Process
  3. Lecture 3: Planning by Dynamic Programming
  4. Lecture 4: Model-Free Prediction
  5. Lecture 5: Model Free Control
  6. Lecture 6: Value Function Approximation
  7. Lecture 7: Policy Gradient Methods
  8. Lecture 8: Integrating Learning and Planning
  9. Lecture 9: Exploration and Exploitation
  10. Lecture 10: Classic Games

OpenSpiel

References

  1. Example of a simple Markov decision processes with three states (green circles) and two actions (orange circles), with two rewards (orange arrows), image by waldoalvarez CC BY-SA 4.0, Wikimedia Commons
  2. Q-learning from Wikipedia
  3. Chris Watkins, Peter Dayan (1992). Q-learning. Machine Learning, Vol. 8, No. 2
  4. Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, Demis Hassabis (2015). Human-level control through deep reinforcement learning. Nature, Vol. 518
  5. Q-learning from Wikipedia
  6. Gerald Tesauro (1995). Temporal Difference Learning and TD-Gammon. Communications of the ACM, Vol. 38, No. 3
  7. University of Bristol - Department of Computer Science - Technical Reports
  8. Ms. Pac-Man from Wikipedia
  9. Demystifying Deep Reinforcement Learning by Tambet Matiisen, Nervana, December 22, 2015
  10. Patent US20150100530 - Methods and apparatus for reinforcement learning - Google Patents
  11. DeepChess: Another deep-learning based chess program by Matthew Lai, CCC, October 17, 2016
  12. ICANN 2016 | Recipients of the best paper awards
  13. AlphaGo Zero: Learning from scratch by Demis Hassabis and David Silver, DeepMind, October 18, 2017
  14. AlphaZero: Shedding new light on the grand games of chess, shogi and Go by David Silver, Thomas Hubert, Julian Schrittwieser and Demis Hassabis, DeepMind, December 03, 2018
  15. open_spiel/contributing.md at master · deepmind/open_spiel · GitHub
  16. New DeepMind paper by GregNeto, CCC, November 21, 2019
  17. e: Board adaptive / tuning evaluation function - no NN/AI by Tony P., CCC, January 15, 2020
  18. MuZero: Mastering Go, chess, shogi and Atari without rules
  19. Marc Lanctot, Edward Lockhart, Jean-Baptiste Lespiau, Vinicius Zambaldi, Satyaki Upadhyay, Julien Pérolat, Sriram Srinivasan, Finbarr Timbers, Karl Tuyls, Shayegan Omidshafiei, Daniel Hennes, Dustin Morrill, Paul Muller, Timo Ewalds, Ryan Faulkner, János Kramár, Bart De Vylder, Brennan Saeta, James Bradbury, David Ding, Sebastian Borgeaud, Matthew Lai, Julian Schrittwieser, Thomas Anthony, Edward Hughes, Ivo Danihelka, Jonah Ryan-Davis (2019). OpenSpiel: A Framework for Reinforcement Learning in Games. arXiv:1908.09453

Up one Level