Partially Observable Planning and Learning for Systems with Non-Uniform Dynamics

no code implementations • 9 Jul 2019 • Nicholas Collins, Hanna Kurniawati

We propose a neural network architecture, called TransNet, that combines planning and model learning for solving Partially Observable Markov Decision Processes (POMDPs) with non-uniform system dynamics.

Robot Navigation

The Stability of the Point Spread Function of the Advanced Camera for Surveys on the Hubble Space Telescope and Implications for Weak Gravitational Lensing

no code implementations • 6 Feb 2007 • Jason D. Rhodes, Richard Massey, Justin Albert, Nicholas Collins, Richard S. Ellis, Catherine Heymans, Jonathan P. Gardner, Jean-Paul Kneib, Anton Koekemoer, Alexie Leauthaud, Yannick Mellier, Alexandre Refregier, James E. Taylor, Ludovic van Waerbeke

We derive a parametric correction for the effect of CTE on the shapes of objects in the COSMOS field as a function of observation date, position within the ACS WFC field, and object flux.