publications

Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning.
Michael Teng, Michiel van de Panne, and Frank Wood.
arXiv:2202.02693, 2022 [Link]

A Closer Look at Gradient Estimators with Reinforcement Learning as Inference.
Jonathan Wilder Lavington, Michael Teng, Mark Schmidt, and Frank Wood.
NeurIPS DeepRL Workshop, 2021 [Link]

Semi-supervised Sequential Generative Models.
Michael Teng, Tuan Anh Le, Adam Scibior and Frank Wood.
Uncertainty in Artificial Intelligence (UAI), PMLR 124:649-658, 2020 [Link]

Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training.
Will Harvey, Michael Teng, and Frank Wood.
arXiv:1906.05462, 2020. [Link]

Bayesian Distributed Stochastic Gradient Descent.
Michael Teng and Frank Wood.
Neural Information Processing Systems (NeurIPS) 31:6378-6388, 2018. [Link]

Poloxamer 188 Decreases Membrane Toxicity of Mutant SOD1 and Ameliorates Pathology Observed in SOD1 Mouse Model for ALS.
J. J. Riehm, L. Wang, G. Ghadge, M. Teng, A. M. Correa, J. D. Marks, R. P. Roos, and M. J. Allen.
Neurobiology of Disease 115:115-126, 2018. [Link]

Nonintercalating Nanosubstrates Create Asymmetry Between Bilayer Leaflets.
Sameer Varma, Michael Teng, and H. Larry Scott.
Langmuir 28.5:2842-2848, 2012. [Link]