Search Results for author: Michael Teng

Found 7 papers, 0 papers with code

Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning

no code implementations6 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.

Continuous Control Distributional Reinforcement Learning +3

Near-Optimal Glimpse Sequences for Training Hard Attention Neural Networks

no code implementations1 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.

Experimental Design General Classification +2

Semi-supervised Sequential Generative Models

no code implementations30 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.

Time Series Time Series Analysis

Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training

no code implementations13 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.

Experimental Design General Classification +2

Imitation Learning of Factored Multi-agent Reactive Models

no code implementations12 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.

Imitation Learning

Bayesian Distributed Stochastic Gradient Descent

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.

High Throughput Synchronous Distributed Stochastic Gradient Descent

no code implementations12 Mar 2018 Michael Teng, Frank Wood

We introduce a new, high-throughput, synchronous, distributed, data-parallel, stochastic-gradient-descent learning algorithm.

Vocal Bursts Intensity Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.