Acontinual learning agent learns online with anon-stationary andnever-ending stream ofdata. Thekeytosuch learning process istoovercome thecatastrophic forgetting of previously seen data, which is a well known problem of neuralnetworks.

In this paper we consider the dynamic assortment selection problem under an uncapacitated multinomial-logit (MNL) model. By carefully analyzing a revenue potential function, we show that a trisection based algorithm achieves an item-independent regret bound of Op? T log log T q, which matches information theoretical lower bounds up to iterated logarithmic terms. Our proof technique draws tools from the unimodal/convex bandit literature as well as adaptive confidence parameters in minimax multi-armed bandit problems.

While conceptually simple, we show that in practice, this reward modeling requires careful algorithmic considerations around model architecture and reward scaling.

Neural Information Processing Systems http://nips.cc/

Deep neural networks have been found to be vulnerable in a variety of tasks. Adversarial attacks can manipulate network outputs, resulting in incorrect predictions.

Neural Information Processing Systems http://nips.cc/

Due to limited time, we evaluated SNM [Yin and Neubig, 2017] on Python dataset.5 SNM explicitly introduces the constraints of grammar rules when generating ASTs. The BLEU score for SNM is6 10.62 and similar to our Basic model, indicating that the CG task on this dataset is very challenging. In particular,7 all prediction of SNM is valid, whereas the percentage of valid code generated by the dual model is low (Table 1).8 Since CS and CG models are trained at the same time and the parameters of the36 two models are separate after the joint training, i.e., the two models solve their respective tasks separately after the37 joint training, the number of parameters of each dual model is the same as that of the basic model.

Neural Information Processing Systems http://nips.cc/