http://www.bibsonomy.org/burst/user/schaulBibSonomy BuRST Feed for /user/schaul2008-07-21T01:19:00+02:00idsiahttp://www.bibsonomy.org/bibtex/28969aae0ed7d0829c17ce7411f2bcdc7/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">Nate <a href="http://www.bibsonomy.org/author/Kohl">Kohl</a> and Peter <a href="http://www.bibsonomy.org/author/Stone">Stone</a> </span><em>Proceedings of the IEEE International Conference on Robotics and Automation, </em><em>May2004. </em>Tue Feb 26 12:05:08 CET 2008Proceedings of the IEEE International Conference on Robotics and AutomationMayPolicy Gradient Reinforcement Learning for Fast Quadrupedal Locomotion2004daanbib idsiahttp://www.bibsonomy.org/bibtex/28192988ef1ed0e526026b14386579030/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">Shimon <a href="http://www.bibsonomy.org/author/Whiteson">Whiteson</a> and Nate <a href="http://www.bibsonomy.org/author/Kohl">Kohl</a> and Risto <a href="http://www.bibsonomy.org/author/Miikkulainen">Miikkulainen</a> and Peter <a href="http://www.bibsonomy.org/author/Stone">Stone</a> </span><em>Machine Learning</em><em>59(1):5--30</em><em>May2005. </em>Tue Feb 26 12:05:08 CET 2008Machine LearningMay15--30Evolving Keepaway Soccer Players through Task Decomposition592005daanbib idsiahttp://www.bibsonomy.org/bibtex/2ba7d96561c76b3ef903c9058197cd1c1/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">M. <a href="http://www.bibsonomy.org/author/Ghavamzadeh">Ghavamzadeh</a> and Sridhar <a href="http://www.bibsonomy.org/author/Mahadevan">Mahadevan</a> </span><em>Proceedings of the Twentieth Conference on Machine Learning (ICML-2003), </em>(<em>2003</em>)Tue Feb 26 12:05:08 CET 2008Proceedings of the Twentieth Conference on Machine Learning (ICML-2003)Hierarchical Policy Gradient Algorithms2003daanbib idsiahttp://www.bibsonomy.org/bibtex/297049a49146280b30b45e0115b08ac7d/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">Peter <a href="http://www.bibsonomy.org/author/Stone">Stone</a> and Richard S. <a href="http://www.bibsonomy.org/author/Sutton">Sutton</a> and Gregory <a href="http://www.bibsonomy.org/author/Kuhlmann">Kuhlmann</a> </span><em>Adaptive Behavior</em><em>13(3):165--188</em>(<em>2005</em>)Tue Feb 26 12:05:08 CET 2008Adaptive Behavior3165--188Reinforcement Learning for {R}obo{C}up-Soccer Keepaway132005daanbib idsiahttp://www.bibsonomy.org/bibtex/23e75c517832b18be3e327c098df1adfd/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">B. <a href="http://www.bibsonomy.org/author/Bakker">Bakker</a> </span><em>Advances in Neural Information Processing Syst., 14, </em>(<em>2002</em>)Tue Feb 26 12:05:08 CET 2008Advances in Neural Information Processing Syst., 14Reinforcement learning with long short-term memory2002daanbib idsiahttp://www.bibsonomy.org/bibtex/2b16e56cb675bc395c0b868e659f6ed26/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">J. <a href="http://www.bibsonomy.org/author/Peters">Peters</a> and S. <a href="http://www.bibsonomy.org/author/Vijayakumar">Vijayakumar</a> and S. <a href="http://www.bibsonomy.org/author/Schaal">Schaal</a> </span><em>Proceedings of the 16th European Conference on Machine Learning (ECML 2005), </em><em>page280--291. </em>(<em>2005</em>)Tue Feb 26 12:05:08 CET 2008Proceedings of the 16th European Conference on Machine Learning (ECML 2005)280--291Natural Actor-Critic2005daanbib idsiahttp://www.bibsonomy.org/bibtex/2aa96bdfd16e9593aec3eab071e445966/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">Nicol <a href="http://www.bibsonomy.org/author/Schraudolph">Schraudolph</a> and Jin <a href="http://www.bibsonomy.org/author/Yu">Yu</a> and Douglas <a href="http://www.bibsonomy.org/author/Aberdeen">Aberdeen</a> </span><em>Advances in Neural Information Processing Systems 18, </em><em>MIT Press, </em><em>Cambridge, MA, </em>(<em>2006</em>)Tue Feb 26 12:05:08 CET 2008Cambridge, MAAdvances in Neural Information Processing Systems 18Fast Online Policy Gradient Learning with SMD Gain Vector Adaptation2006daanbib idsiahttp://www.bibsonomy.org/bibtex/2255f2c6da1a8995e57d60a697219992e/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">L. <a href="http://www.bibsonomy.org/author/Baird">Baird</a> </span>(<em>1999</em>)Tue Feb 26 12:05:08 CET 2008Reinforcement Learning Through Gradient Descent1999daanbib idsiahttp://www.bibsonomy.org/bibtex/241406f69681b40d610664492e3dc4d1c/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">R. J. <a href="http://www.bibsonomy.org/author/Williams">Williams</a> and D. <a href="http://www.bibsonomy.org/author/Zipser">Zipser</a> </span><em>Neural Computation</em><em>1(2):270--280</em>(<em>1989</em>)Tue Feb 26 12:05:08 CET 2008Neural Computation2270--280A learning algorithm for continually running fully recurrent networks11989daanbib idsiahttp://www.bibsonomy.org/bibtex/22548e25c4316e6d365a1cda13910c7b1/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">J. <a href="http://www.bibsonomy.org/author/Schmidhuber">Schmidhuber</a> and F. <a href="http://www.bibsonomy.org/author/Gers">Gers</a> and D. <a href="http://www.bibsonomy.org/author/Eck">Eck</a> </span><em>Neural Computation</em><em>14(9):2039--2041</em>(<em>2002</em>)Tue Feb 26 12:05:08 CET 2008Neural Computation92039--2041Learning Nonregular Languages: A Comparison of Simple Recurrent Networks and {LSTM}142002daanbib idsiahttp://www.bibsonomy.org/bibtex/279df6721c014a00bfac62abd7d5a9968/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">S. <a href="http://www.bibsonomy.org/author/Hochreiter">Hochreiter</a> and Y. <a href="http://www.bibsonomy.org/author/Bengio">Bengio</a> and P. <a href="http://www.bibsonomy.org/author/Frasconi">Frasconi</a> and J. <a href="http://www.bibsonomy.org/author/Schmidhuber">Schmidhuber</a> </span><em>A Field Guide to Dynamical Recurrent Neural Networks, </em><em>IEEE Press, </em>(<em>2001</em>)Tue Feb 26 12:05:08 CET 2008A Field Guide to Dynamical Recurrent Neural NetworksGradient flow in recurrent nets: the difficulty of learning long-term dependencies2001daanbib idsiahttp://www.bibsonomy.org/bibtex/2825192e2b52551362862b4b20fbbea1c/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">J. <a href="http://www.bibsonomy.org/author/Schmidhuber">Schmidhuber</a> </span>(<em>2004</em>)Tue Feb 26 12:05:08 CET 2008{RNN} overview2004daanbib idsiahttp://www.bibsonomy.org/bibtex/2308dfb505e23a977417d69d6a94d1cad/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">V. <a href="http://www.bibsonomy.org/author/Gullapalli">Gullapalli</a> </span>(<em>1992</em>)Tue Feb 26 12:05:08 CET 2008Reinforcement learning and its application to control1992daanbib idsiahttp://www.bibsonomy.org/bibtex/2b03f900e582e764963efe48e4d76f0bc/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">J. <a href="http://www.bibsonomy.org/author/Klockgether">Klockgether</a> and H. P. <a href="http://www.bibsonomy.org/author/Schwefel">Schwefel</a> </span><em>Proc. 11th Symp. Engineering Aspects of Magnetohydrodynamics, </em><em>page141--148. </em>(<em>1970</em>)Tue Feb 26 12:05:08 CET 2008Proc. 11th Symp. Engineering Aspects of Magnetohydrodynamics141--148Two-phase nozzle and hollow core jet experiments1970daanbib idsiahttp://www.bibsonomy.org/bibtex/20a13668f6995399e22b001c9eeba0b7a/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">James C. <a href="http://www.bibsonomy.org/author/Spall">Spall</a> </span><em>WSC '99: Proceedings of the 31st conference on Winter simulation, </em><em>page101--109. </em><em>New York, NY, USA, </em><em>ACM, </em>(<em>1999</em>)Tue Feb 26 12:05:08 CET 2008New York, NY, USAWSC '99: Proceedings of the 31st conference on Winter simulation101--109Stochastic optimization and the simultaneous perturbation method1999daanbib idsiahttp://www.bibsonomy.org/bibtex/299396210934937d279f29a0e10f9ee8f/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">James <a href="http://www.bibsonomy.org/author/Kennedy">Kennedy</a> and Russell C. <a href="http://www.bibsonomy.org/author/Eberhart">Eberhart</a> </span><em>Morgan Kaufmann Publishers Inc., </em><em>San Francisco, CA, USA, </em>(<em>2001</em>)Tue Feb 26 12:05:08 CET 2008San Francisco, CA, USASwarm intelligence2001daanbib idsiahttp://www.bibsonomy.org/bibtex/2bf34d745d798e80585c4590e621fcd37/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">S. <a href="http://www.bibsonomy.org/author/Kirkpatrick">Kirkpatrick</a> and C. D. <a href="http://www.bibsonomy.org/author/Gelatt">Gelatt</a> and M. P. <a href="http://www.bibsonomy.org/author/Vecchi">Vecchi</a> </span><em>Science, Number 4598, 13 May 1983</em>(<em>1983</em>)Tue Feb 26 12:05:08 CET 2008Science, Number 4598, 13 May 1983671--680Optimization by Simulated Annealing220, 45981983daanbib idsiahttp://www.bibsonomy.org/bibtex/204cab5fc779db34f662a2ae0f25e96ad/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">S. <a href="http://www.bibsonomy.org/author/Amari">Amari</a> </span><em>Neural Computation</em><em>10(2):251--276</em>(<em>1998</em>)Tue Feb 26 12:05:08 CET 2008Neural Computation2251--276Natural Gradient Works Efficiently in Learning101998daanbib idsiahttp://www.bibsonomy.org/bibtex/2143b3278d469900d7b42be66c0611739/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">Verena H. <a href="http://www.bibsonomy.org/author/Meisner">Meisner</a> and Christian <a href="http://www.bibsonomy.org/author/Igel">Igel</a> </span><em>To appear in: 16th European Symposium on Artificial Neural Networks (ESANN), </em>(<em>2008</em>)Tue Feb 26 12:05:08 CET 2008To appear in: 16th European Symposium on Artificial Neural Networks (ESANN)Similarities and differences between policy gradient methods and evolution strategies2008daanbib idsiahttp://www.bibsonomy.org/bibtex/26ed054d7babe82af8c357947ba30f660/schaulschaul2008-02-26T12:05:08+01:00daanbib <span style="color:#555555;">P. <a href="http://www.bibsonomy.org/author/De Boer">De Boer</a> and <a href="http://www.bibsonomy.org/author/Kroese">Kroese</a> and S. <a href="http://www.bibsonomy.org/author/Mannor">Mannor</a> and R. Y. <a href="http://www.bibsonomy.org/author/Rubinstein">Rubinstein</a> </span><em>Annals of Operations Research, </em><em>134, </em><em>page19--67. </em>(<em>2004</em>)Tue Feb 26 12:05:08 CET 2008Annals of Operations Research119--67A Tutorial on the Cross-Entropy Method1342004daanbib