no code implementations • 6 Feb 2022 • Michael Teng, Michiel Van de Panne, Frank Wood
Distributional reinforcement learning (RL) aims to learn a value-network that predicts the full distribution of the returns for a given state, often modeled via a quantile-based critic.
no code implementations • 1 Jan 2021 • William Harvey, Michael Teng, Frank Wood
We introduce methodology from the BOED literature to approximate this optimal behaviour, and use it to generate `near-optimal' sequences of attention locations.
no code implementations • 30 Jun 2020 • Michael Teng, Tuan Anh Le, Adam Scibior, Frank Wood
We introduce a novel objective for training deep generative time-series models with discrete latent variables for which supervision is only sparsely available.
no code implementations • 13 Jun 2019 • William Harvey, Michael Teng, Frank Wood
We introduce methodology from the BOED literature to approximate this optimal behaviour, and use it to generate `near-optimal' sequences of attention locations.
no code implementations • 12 Mar 2019 • Michael Teng, Tuan Anh Le, Adam Scibior, Frank Wood
We apply recent advances in deep generative modeling to the task of imitation learning from biological agents.
no code implementations • NeurIPS 2018 • Michael Teng, Frank Wood
We introduce Bayesian distributed stochastic gradient descent (BDSGD), a high-throughput algorithm for training deep neural networks on parallel clusters.
no code implementations • 12 Mar 2018 • Michael Teng, Frank Wood
We introduce a new, high-throughput, synchronous, distributed, data-parallel, stochastic-gradient-descent learning algorithm.