5 papers
Robust Asymmetric Learning in POMDPs
Andrew Warrington, J. Wilder Lavington, Adam Ścibior +2
Policies for partially observed Markov decision processes can be efficiently learned by imitating policies for the corresponding fully observed Markov decision processes. Unfortuna…
Coping With Simulators That Don't Always Return
Andrew Warrington, Saeid Naderiparizi, Frank Wood
Deterministic models are approximations of reality that are easy to interpret and often easier to build than stochastic alternatives. Unfortunately, as nature is capricious, observ…
The Virtual Patch Clamp: Imputing C. elegans Membrane Potentials from Calcium Imaging
Andrew Warrington, Arthur Spencer, Frank Wood
We develop a stochastic whole-brain and body simulator of the nematode roundworm Caenorhabditis elegans (C. elegans) and show that it is sufficiently regularizing to allow imputati…
Generalising Cost-Optimal Particle Filtering
Andrew Warrington, Neil Dhir
We present an instance of the optimal sensor scheduling problem with the additional relaxation that our observer makes active choices whether or not to observe and how to observe.…
Updating the VESICLE-CNN Synapse Detector
Andrew Warrington, Frank Wood
We present an updated version of the VESICLE-CNN algorithm presented by Roncal et al. (2014). The original implementation makes use of a patch-based approach. This methodology is k…