Learning to Select from Multiple Options

Learning to select computations

Efficient use of limited computational resources is essential to intelligence. Selecting computations optimally according to rational metareasoning would achieve this, but rational metareasoning is computationally intractable. Inspired by psychology and neuroscience, we propose the first learning algorithm for approximating the optimal selection of computations. We derive a general, sample-effi...

Learning to Select Useful

To navigate eeectively, an autonomous agent must be able to quickly and accurately determine its current location. Given an initial estimate of its position (perhaps based on dead-reckoning) and an image taken of a known environment, our agent rst attempts to locate a set of landmarks (real-world objects at known locations), then uses their angular separation to obtain an improved estimate of i...

How to select among available options for the treatment of multiple myeloma.

The introduction of novel agents (thalidomide, bortezomib and lenalidomide) in the frontline therapy of multiple myeloma has markedly improved the outcome both in younger patients who are candidates for high-dose therapy plus autologous stem-cell transplantation (HDT/ASCT) and in elderly patients. In the HDT/ASCT paradigm, novel agents may be used as induction therapy or after HDT/ASCT as conso...

Learning to Select Useful Landmarks

Learning to Select Useful Landmarks

To navigate effectively, an autonomous agent must be able to quickly and accurately determine its current location. Given an initial estimate of its position (perhaps based on dead-reckoning) and an image taken of a known environment, our agent first attempts to locate a set of landmarks (real-world objects at known locations), then uses their angular separation to obtain an improved estimate o...