Matthew W. Hoffman

I’m a research scientist at DeepMind where I work on reinforcement learning and sequential decision making problems.

Recent News

• June 2, 2020. Along with some great colleagues at DeepMind we’re releasing Acme, an RL framework that we’ve been working on and using for our own research for quite some time. You can check it out here or take a look at our whitepaper!

• January 15, 2019. I have finally gotten around to moving and updating my website. At the moment the data here should be incredibly out-of-date, but it’s only a matter of time before the rest gets updated! (Thanks to Yannis for forcing me to do this!)

• August 12, 2016. Our paper on Learning to learn by gradient descent by gradient descent was accepted at NIPS 2016. See you in Barcelona!

Recent publications and preprints

1. Hoffman, M., Shahriari, B., Aslanides, J., Barth-Maron, G., Behbahani, F., Norman, T., Abdolmaleki, A., Cassirer, A., Yang, F., Baumli, K., Henderson, S., Novikov, A., Colmenarejo, S. G., Cabi, S., Gulcehre, C., Paine, T. L., Cowie, A., Wang, Z., Piot, B., and de Freitas, N. (2020). Acme: A Research Framework for Distributed Reinforcement Learning. arXiv:2006.00979. [pdf] [bibtex]

   @techreport{hoffman:2020,
     title = {Acme: A Research Framework for Distributed Reinforcement Learning},
     author = {Hoffman, Matt and Shahriari, Bobak and Aslanides, John and Barth-Maron, Gabriel and Behbahani, Feryal and Norman, Tamara and Abdolmaleki, Abbas and Cassirer, Albin and Yang, Fan and Baumli, Kate and Henderson, Sarah and Novikov, Alex and Colmenarejo, Sergio Gómez and Cabi, Serkan and Gulcehre, Caglar and Paine, Tom Le and Cowie, Andrew and Wang, Ziyu and Piot, Bilal and de Freitas, Nando},
     year = {2020},
     month = jun,
     howpublished = {arXiv:2006.00979},
     link = {https://arxiv.org/pdf/2006.00979.pdf}
   }
   

2. Gu, A., Gulcehre, C., Paine, T. L., Hoffman, M., and Pascanu, R. (2019). Improving the Gating Mechanism of Recurrent Neural Networks. arXiv:1910.09890. [pdf] [bibtex]

   @techreport{gu:2019,
     title = {Improving the Gating Mechanism of Recurrent Neural Networks},
     author = {Gu, Albert and Gulcehre, Caglar and Paine, Tom Le and Hoffman, Matt and Pascanu, Razvan},
     year = {2019},
     month = oct,
     howpublished = {arXiv:1910.09890},
     link = {https://arxiv.org/pdf/1910.09890.pdf}
   }
   

3. Paine, T. L., Gulcehre, C., Shahriari, B., Denil, M., Hoffman, M., Soyer, H., Tanburn, R., Kapturowski, S., Rabinowitz, N., Williams, D., Barth-Maron, G., Wang, Z., de Freitas, N., and Team, W. (2019). Making Efficient Use of Demonstrations to Solve Hard Exploration Problems. arXiv:1909.01387. [pdf] [bibtex]

   @techreport{paine:2019,
     title = {Making Efficient Use of Demonstrations to Solve Hard Exploration
         Problems},
     author = {Paine, Tom Le and Gulcehre, Caglar and Shahriari, Bobak and Denil, Misha and Hoffman, Matt and Soyer, Hubert and Tanburn, Richard and Kapturowski, Steven and Rabinowitz, Neil and Williams, Duncan and Barth-Maron, Gabriel and Wang, Ziyu and de Freitas, Nando and Team, Worlds},
     year = {2019},
     month = oct,
     howpublished = {arXiv:1909.01387},
     link = {https://arxiv.org/pdf/1909.01387.pdf}
   }