PAC-Bayesian Analysis of the Exploration-Exploitation Trade-off
Yevgeny Seldin, Nicolò Cesa-Bianchi, François Laviolette, Peter Auer, John Shawe-Taylor and Jan Peters
In: On‐line Trading of Exploration and Exploitation 2 – ICML 2011, 2 July 2011, Bellevue, Washington, USA.
We develop a coherent framework for integrative simultaneous analysis of the exploration-exploitation and model order selection trade-offs. We improve over our preceding results on the same subject (Seldin et. al., 2011) by combining PAC-Bayesian analysis with Bernstein-type inequality for martingales. Such a combination is also of independent interest for studies of multiple simultaneously evolving martingales.