Metacontrol for adaptive imagination-based optimization

5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings

Volumn , Issue , 2017, Pages

  Hamrick, Jessica B ^a   Ballard, Andrew J ^a   Pascanu, Razvan ^a   Vinyals, Oriol ^a   Heess, Nicolas ^a   Battaglia, Peter W ^a  

^a DEEPMIND   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

BUDGET CONTROL; DECISION MAKING; MACHINE LEARNING;

COMPUTATIONAL BUDGET; COMPUTATIONAL RESOURCES; DECISION-MAKING PROBLEM; INTERACTION NETWORKS; MODEL-BASED REINFORCEMENT LEARNING; OPTIMIZATION PROCEDURES; REINFORCEMENT LEARNING AGENT; STATE TRANSITION MODELS;

REINFORCEMENT LEARNING;

EID: 85087796046     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et al. TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. URL http://tensorflow.org/. Software available from tensorflow.org.
2. Peter Battaglia, Razvan Pascanu, Matthew Lai, Danilo Jimenez Rezende, and Koray Kavukcuoglu. Interaction networks for learning about objects, relations and physics. Advances in Neural Information Processing Systems, 2016.
3. Alex Graves. Adaptive computation time for recurrent neural networks. arXiv:1603.08983, 2016.
4. Nicholas Hay, Stuart J. Russell, David Tolpin, and Solomon Eyal Shimony. Selecting computations: Theory and applications. Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, 2012.
5. Nicolas Heess, Gregory Wayne, David Silver, Tim Lillicrap, Tom Erez, and Yuval Tassa. Learning continuous control policies by stochastic value gradients. Advances in Neural Information Processing Systems, 2015.
6. Diederik Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv:1412.6980, 2014.
7. Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. Asynchronous methods for deep reinforcement learning. Proceedings of the 33rd International Conference on Machine Learning, 2016.
8. Razvan Pascanu, Tomas Mikolov, and Yoshua Bengio. On the difficulty of training recurrent neural networks. Proceedings of the 27st International Conference on Machine Learning, pp. 1310-1318, 2013.
9. Stuart Russell and Eric Wefald. Principles of metareasoning. Artificial Intelligence, 49(1):361 - 395, 1991.
10. Aäron van den Oord, Nal Kalchbrenner, Oriol Vinyals, Lasse Espeholt, Alex Graves, and Koray Kavukcuoglu. Conditional image generation with PixelCNN decoders. arXiv:1606.05328, 2016.
11. Ronald J. Williams. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3-4):229-256, 1992.
12. Ronald J. Williams and Jing Peng. Function optimization using connectionist reinforcement learning algorithms. Connection Science, 3(3):241-268, 1991.