Hierarchical task decomposition through symbiosis in reinforcement learning
作者： John A. Doucette , Peter Lichodzijewski , Malcolm I. Heywood
关键词: Computer science 、 Context (language use) 、 Genetic programming 、 Sequence learning 、 Generalization 、 Task (project management) 、 Machine learning 、 Artificial intelligence 、 Reinforcement learning
摘要: … Such a separation provides a mechanism for task decomposition in temporal sequence … policy trees. A benchmarking study is performed using the Acrobot handstand task. Solutions to …
acm.org
sci-hub.se 参考文章(23)
Rémi Coulom, High-Accuracy Value-Function Approximation with Neural Networks Applied to the Acrobot the european symposium on artificial neural networks. pp. 7- 12 ,(2004)
Damien Ernst, Arthur Louette, Introduction to Reinforcement Learning MIT Press. ,(1998)
Herbert A. Simon, The Architecture of Complexity Facets of Systems Science. ,vol. 106, pp. 457- 476 ,(1991) , 10.1007/978-1-4899-0718-9_31
Yaakov Engel, Gaussian Process Reinforcement Learning. Encyclopedia of Machine Learning. pp. 439- 447 ,(2010)
John J. Grefenstette, David E. Moriarty, Alan C. Schultz, Evolutionary algorithms for reinforcement learning Journal of Artificial Intelligence Research. ,vol. 11, pp. 241- 276 ,(1999) , 10.1613/JAIR.613
Stephen Kelly, Peter Lichodzijewski, Malcolm I. Heywood, On run time libraries and hierarchical symbiosis congress on evolutionary computation. pp. 1- 8 ,(2012) , 10.1109/CEC.2012.6252966
Mark W Spong, The swing up control problem for the Acrobot IEEE Control Systems Magazine. ,vol. 15, pp. 49- 55 ,(1995) , 10.1109/37.341864
Kazuo Kawada, Masanobu Obika, Shoichiro Fujisawa, Toru Yamamoto, Yasuhiro Mada, Creating Swing-Up Patterns of an Acrobot Using Evolutionary Computation Ieej Transactions on Electronics, Information and Systems. ,vol. 125, pp. 457- 462 ,(2005) , 10.1541/IEEJEISS.125.457
J. Yoshimoto, S. Ishii, M. Sato, Application of reinforcement learning to balancing of Acrobot systems man and cybernetics. ,vol. 5, pp. 516- 521 ,(1999) , 10.1109/ICSMC.1999.815605
Pierre-Yves Oudeyer, Frdric Kaplan, Verena V. Hafner, Intrinsic Motivation Systems for Autonomous Mental Development IEEE Transactions on Evolutionary Computation. ,vol. 11, pp. 265- 286 ,(2007) , 10.1109/TEVC.2006.890271