摘要: We propose the neural programmer-interpreter (NPI): a recurrent and compositional neural network that learns to represent and execute programs. NPI has three learnable …
arxiv.org参考文章(26)
Tom Schaul, Daniel Horgan, David Silver, Karol Gregor, Universal Value Function Approximators international conference on machine learning. pp. 1312- 1320 ,(2015)
Ilya Sutskever, Wojciech Zaremba, Learning to Execute arXiv: Neural and Evolutionary Computing. ,(2014)
Francesco Donnarumma, Roberto Prevete, Fabian Chersi, Giovanni Pezzulo, A Programmer-Interpreter Neural Network Architecture for Prefrontal Cognitive Control. International Journal of Neural Systems. ,vol. 25, pp. 1550017- 1550017 ,(2015) , 10.1142/S0129065715500173
Sepp Hochreiter, Jürgen Schmidhuber, Long short-term memory Neural Computation. ,vol. 9, pp. 1735- 1780 ,(1997) , 10.1162/NECO.1997.9.8.1735
Pieter Abbeel, Andrew Y. Ng, J. Z. Kolter, Hierarchical Apprenticeship Learning with Application to Quadruped Locomotion neural information processing systems. ,vol. 20, pp. 769- 776 ,(2007)
Richard S. Sutton, Doina Precup, Satinder Singh, Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning Artificial Intelligence. ,vol. 112, pp. 181- 211 ,(1999) , 10.1016/S0004-3702(99)00052-1
Sanja Fidler, Sven Dickinson, Raquel Urtasun, 3D Object Detection and Viewpoint Estimation with a Deformable 3D Cuboid Model neural information processing systems. ,vol. 25, pp. 611- 619 ,(2012)
Francesco Donnarumma, Roberto Prevete, Giuseppe Trautteur, Programming in the brain: a neural network theoretical framework Connection Science. ,vol. 24, pp. 71- 90 ,(2012) , 10.1080/09540091.2012.684670
T. G. Dietterich, Hierarchical reinforcement learning with the MAXQ value function decomposition Journal of Artificial Intelligence Research. ,vol. 13, pp. 227- 303 ,(2000) , 10.1613/JAIR.639
Ilya Sutskever, Quoc V. Le, Oriol Vinyals, Sequence to Sequence Learning with Neural Networks neural information processing systems. ,vol. 27, pp. 3104- 3112 ,(2014)