Resources

542

Kappel, D., Legenstein, R., Habenschuss, S., Hsieh, M. & Maass, W. Reward-based stochastic self-configuration of neural circuits. arXiv:1704.04238 [cs, q-bio] (2017). (https://arxiv.org/abs/1704.04238)

Resources related to Heidelberg Hardware

Optimizers

• NIPS 2016 tutorial on Deep Reinforcement Learning

Cross Entropy

• Implementation of Cross Entropy in R -- Benham, Tim, et al. "CEoptim: Cross-Entropy R Package for Optimization." arXiv preprint arXiv:1503.01842 (2015).
• Tetris paper containing the most basic version of Cross Entropy -- Szita, István, and András Lörincz. "Learning Tetris using the noisy cross-entropy method." Neural computation 18.12 (2006): 2936-2941.(pdf)
• Extension of the Tetris CE paper -- Thiery, Christophe, and Bruno Scherrer. "Improvements on learning Tetris with cross entropy." Icga Journal 32.1 (2009): 23-33.
• Extensive tutorial: Boer, P.-T. de, Kroese, D. P., Mannor, S. & Rubinstein, R. Y. A Tutorial on the Cross-Entropy Method. Ann Oper Res 134, 19–67 (2005).

Functions

• Paper containing the list of functions -- Onbaşoğlu, Esin, and Linet Özdamar. "Parallel simulated annealing algorithms in global optimization." Journal of Global Optimization 19.1 (2001): 27-50.(pdf)