publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
2017
- Data-efficient deep reinforcement learning for dexterous manipulationarXiv preprint arXiv:1704.03073 2017
- Diego de Las Casas, Andreas Fidjeland, Tim Green, Adrià Puigdomènech, Sébastien Racanière, Jack Rae, and Fabio Viola. Open sourcing Sonnet-a new library for constructing neural networks2017
2018
- Distributed prioritized experience replayarXiv preprint arXiv:1803.00933 2018
- Distributed distributional deterministic policy gradientsarXiv preprint arXiv:1804.08617 2018
- Observe and look further: Achieving consistent performance on atariarXiv preprint arXiv:1805.11593 2018
- One-shot high-fidelity imitation: Training large-scale deep nets with rlarXiv preprint arXiv:1810.05017 2018
- Towards Consistent Performance on Atari using Expert Demonstrations2018
2019
- Making efficient use of demonstrations to solve hard exploration problemsarXiv preprint arXiv:1909.01387 2019
- Quantized reinforcement learning (quarl)arXiv preprint arXiv:1910.01055 2019
- Making efficient use of demonstrations to solve hard exploration problems2019
- QuaRL: Quantization for sustainable reinforcement learningarXiv e-prints 2019
- Making efficient use of demonstrations to solve hard exploration problemsarXiv e-prints 2019
2020
- Acme: A research framework for distributed reinforcement learningarXiv preprint arXiv:2006.00979 2020
2021
- Reverb: a framework for experience replayarXiv preprint arXiv:2102.04736 2021
- Launchpad: a programming model for distributed machine learning researcharXiv preprint arXiv:2106.04516 2021
2022
- A Generalist AgentarXiv preprint arXiv:2205.06175 2022