Bayesian models and inference for reinforcement learning: the multi-armed bandit case

Abstract:
The most celebrated corners of machine learning over the past decades are those successful at predicting -- e.g. spam classification, medical diagnoses, or cat faces. However, a wide variety of applied problems are prescriptive rather than predictive: those for which decisions must be made in order to maximize a reward. Such problems are common in health, commerce, and engineering. One particular setting for optimizing interactions with the unknown world is the multi-armed bandit, which describes sequential decision processes, a particular instance of reinforcement learning.

In this talk, I will show how Bayesian models and inference methods from the statistics and machine learning community -- particularly variational and Monte Carlo methods -- can be used to extend multi-armed bandit  models, improve learning on complex scenarios, and make informed decisions. 
 

f you want to know more about Iñigo Urteaga, you can visit his web site: https://iurteaga.github.io/