Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Michael Teng

Michael Teng

Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning

Feb 06, 2022
Michael Teng, Michiel van de Panne, Frank Wood

Figure 1 for Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning

Figure 2 for Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning

Figure 3 for Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning

Figure 4 for Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning

* Submitted to ICML 2022

Access Paper or Ask Questions

Semi-supervised Sequential Generative Models

Jun 30, 2020
Michael Teng, Tuan Anh Le, Adam Scibior, Frank Wood

Figure 1 for Semi-supervised Sequential Generative Models

Figure 2 for Semi-supervised Sequential Generative Models

Figure 3 for Semi-supervised Sequential Generative Models

Figure 4 for Semi-supervised Sequential Generative Models

* Accepted to Uncertainty in Artificial Intelligence 2020

Access Paper or Ask Questions

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

Jun 13, 2019
William Harvey, Michael Teng, Frank Wood

Figure 1 for Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training

Figure 2 for Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training

Figure 3 for Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training

Figure 4 for Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training

* 9 pages, 5 figures + appendix with 6 pages, 4 figures.Submitted to NeurIPS 2019

Access Paper or Ask Questions

High Throughput Synchronous Distributed Stochastic Gradient Descent

Mar 12, 2018
Michael Teng, Frank Wood

Figure 1 for High Throughput Synchronous Distributed Stochastic Gradient Descent

Figure 2 for High Throughput Synchronous Distributed Stochastic Gradient Descent

Figure 3 for High Throughput Synchronous Distributed Stochastic Gradient Descent

Figure 4 for High Throughput Synchronous Distributed Stochastic Gradient Descent

Access Paper or Ask Questions