The optimized certainty equivalent (OCE) is a family of risk measures th...
We study reinforcement learning for continuous-time Markov decision proc...
We consider reinforcement learning for continuous-time Markov decision
p...
It has been recently shown in the literature that the sample averages fr...
We study the model-based undiscounted reinforcement learning for partial...
Stochastic gradient Langevin dynamics (SGLD) and stochastic gradient
Ham...
Stochastic gradient Langevin dynamics (SGLD) is a poweful algorithm for
...
We study a multi-armed bandit problem where the rewards exhibit
regime-s...
Langevin dynamics (LD) has been proven to be a powerful technique for
op...
Stochastic gradient Hamiltonian Monte Carlo (SGHMC) is a variant of
stoc...