references.bib

@inproceedings{Schulman2015,
abstract = {In a variety of problems originating in supervised, unsupervised, and reinforcement learning, the loss function is defined by an expectation over a collection of random variables, which might be part of a probabilistic model or the external world. Estimating the gradient of this loss function, using samples, lies at the core of gradient-based learning algorithms for these problems. We introduce the formalism of stochastic computation graphs-directed acyclic graphs that include both deterministic functions and conditional probability distributions- and describe how to easily and automatically derive an unbiased estimator of the loss function's gradient. The resulting algorithm for computing the gradient estimator is a simple modification of the standard backpropagation algorithm. The generic scheme we propose unifies estimators derived in variety of prior work, along with variance-reduction techniques therein. It could assist researchers in developing intricate models involving a combination of stochastic and deterministic operations, enabling, for example, attention, memory, and control actions.},
archivePrefix = {arXiv},
arxivId = {1506.05254},
author = {Schulman, John and Heess, Nicolas and Weber, Theophane and Abbeel, Pieter},
booktitle = {Advances in Neural Information Processing Systems},
eprint = {1506.05254},
issn = {10495258},
title = {{Gradient estimation using stochastic computation graphs}},
year = {2015}
}

@article{mohamed2019monte,
  title={Monte carlo gradient estimation in machine learning},
  author={Mohamed, Shakir and Rosca, Mihaela and Figurnov, Michael and Mnih, Andriy},
  journal={arXiv preprint arXiv:1906.10652},
  year={2019}
}

@book{glasserman1991gradient,
  title={Gradient estimation via perturbation analysis},
  author={Glasserman, Paul and Ho, Yu-Chi},
  volume={116},
  year={1991},
  publisher={Springer Science \& Business Media}
}

@article{kingma2013auto,
  title={Auto-encoding variational bayes},
  author={Kingma, Diederik P and Welling, Max},
  journal={arXiv preprint arXiv:1312.6114},
  year={2013}
}

@article{jang2016categorical,
  title={Categorical reparameterization with gumbel-softmax},
  author={Jang, Eric and Gu, Shixiang and Poole, Ben},
  journal={arXiv preprint arXiv:1611.01144},
  year={2016}
}
@article{maddison2016concrete,
  title={The concrete distribution: A continuous relaxation of discrete random variables},
  author={Maddison, Chris J and Mnih, Andriy and Teh, Yee Whye},
  journal={arXiv preprint arXiv:1611.00712},
  year={2016}
}

@article{weber2019credit,
  title={Credit assignment techniques in stochastic computation graphs},
  author={Weber, Th{\'e}ophane and Heess, Nicolas and Buesing, Lars and Silver, David},
  journal={arXiv preprint arXiv:1901.01761},
  year={2019}
}

@article{haarnoja2018soft,
  title={Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor},
  author={Haarnoja, Tuomas and Zhou, Aurick and Abbeel, Pieter and Levine, Sergey},
  journal={arXiv preprint arXiv:1801.01290},
  year={2018}
}

@article{lillicrap2015continuous,
  title={Continuous control with deep reinforcement learning},
  author={Lillicrap, Timothy P and Hunt, Jonathan J and Pritzel, Alexander and Heess, Nicolas and Erez, Tom and Tassa, Yuval and Silver, David and Wierstra, Daan},
  journal={arXiv preprint arXiv:1509.02971},
  year={2015}
}

@misc{lewis2020retrievalaugmented,
    title={Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks},
    author={Patrick Lewis and Ethan Perez and Aleksandara Piktus and Fabio Petroni and Vladimir Karpukhin and Naman Goyal and Heinrich Küttler and Mike Lewis and Wen-tau Yih and Tim Rocktäschel and Sebastian Riedel and Douwe Kiela},
    year={2020},
    eprint={2005.11401},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}
@article{bunel2018leveraging,
  title={Leveraging grammar and reinforcement learning for neural program synthesis},
  author={Bunel, Rudy and Hausknecht, Matthew and Devlin, Jacob and Singh, Rishabh and Kohli, Pushmeet},
  journal={arXiv preprint arXiv:1805.04276},
  year={2018}
}
@inproceedings{liang2018memory,
  title={Memory augmented policy optimization for program synthesis and semantic parsing},
  author={Liang, Chen and Norouzi, Mohammad and Berant, Jonathan and Le, Quoc V and Lao, Ni},
  booktitle={Advances in Neural Information Processing Systems},
  pages={9994--10006},
  year={2018}
}
@inproceedings{deng2018latent,
  title={Latent alignment and variational attention},
  author={Deng, Yuntian and Kim, Yoon and Chiu, Justin and Guo, Demi and Rush, Alexander},
  booktitle={Advances in Neural Information Processing Systems},
  pages={9712--9724},
  year={2018}
}
@article{doersch2016tutorial,
  title={Tutorial on variational autoencoders},
  author={Doersch, Carl},
  journal={arXiv preprint arXiv:1606.05908},
  year={2016}
}