no code implementations • pproximateinference AABI Symposium 2021 • Marcin B. Tomczak, Richard E Turner
Bayesian learning of neural networks is attractive as it can protecting against over-fitting and provide automatic methods for inferring important hyperparameters by maximizing the marginal probability of the data.
no code implementations • 9 Oct 2019 • Marcin B. Tomczak, Sergio Valcarcel Macua, Enrique Munoz de Cote, Peter Vrancx
In this work we establish conditions under which the parametric approximation of the critic does not introduce bias to the updates of surrogate objective.
1 code implementation • 9 Oct 2019 • Marcin B. Tomczak, Dongho Kim, Peter Vrancx, Kee-Eung Kim
These proxy objectives allow stable and low variance policy learning, but require small policy updates to ensure that the proxy objective remains an accurate approximation of the target policy value.