3 papers
cs.LG2021
Learning to track environment state via predictive autoencoding
Marian Andrecki, Nicholas K. Taylor
This work introduces a neural architecture for learning forward models of stochastic environments. The task is achieved solely through learning from temporal unstructured observati…
cs.LG2020
IV-Posterior: Inverse Value Estimation for Interpretable Policy Certificates
Tatiana Lopez-Guevara, Michael Burke, Nicholas K. Taylor +1
Model-free reinforcement learning (RL) is a powerful tool to learn a broad range of robot skills and policies. However, a lack of policy interpretability can inhibit their successf…
cs.RO2019
To Stir or Not to Stir: Online Estimation of Liquid Properties for Pouring Actions
Tatiana Lopez-Guevara, Rita Pucci, Nicholas Taylor +3
Our brains are able to exploit coarse physical models of fluids to solve everyday manipulation tasks. There has been considerable interest in developing such a capability in robots…