Topic: observations

Hélène Brogniez examines atmospheric water vapour as a major component of the climate system. The seminar explains how its relationship with temperature amplifies warming and connects this feedback to the water cycle. Observations and numerical models are considered as complementary tools for weather prediction and climate projections.

While meta-learning algorithms are often viewed as algorithms that learn to learn, an alternative viewpoint frames meta-learning as inferring a hidden task variable from experience consisting of observations and rewards. From this perspective, learning to learn is learning to infer. This viewpoint can be useful in solving problems in meta-RL, which I’ll demonstrate through two examples: (1) enabling off-policy meta-learning, and (2) performing efficient meta-RL from image observations. I’ll also discuss how this perspective leads to an algorithm for few-shot image segmentation.