no code implementations • 10 Jun 2022 • George Stamatescu
A dynamic mean field theory is developed for finite state and action Bayesian reinforcement learning in the large state space limit.
no code implementations • ICLR 2020 • George Stamatescu, Federica Gerace, Carlo Lucibello, Ian Fuss, Langford B. White
Moreover, we predict theoretically and confirm numerically, that common weight initialisation schemes used in standard continuous networks, when applied to the mean values of the stochastic binary weights, yield poor training performance.
no code implementations • 13 May 2016 • George Stamatescu, Langford B. White, Riley Bruce-Doust
This paper develops Bayesian track extraction algorithms for targets modelled as hidden reciprocal chains (HRC).