12 papers
Generative Modeling by Value-Driven Transport
Pablo Moreno-Muñoz, Adrian Müller, Gergely Neu
We propose a new framework for generative modeling based on a discrete-time stochastic control formulation of measure transport. Adapting classic results from control theory, we fo…
Online learning with ErdÅs-Rényi side-observation graphs
Tomáš Kocák, Gergely Neu, Michal Valko
We consider adversarial multi-armed bandit problems where the learner is allowed to observe losses of a number of arms beside the arm that it actually chose. We study the case wher…
Online combinatorial optimization with stochastic decision sets and adversarial losses
Gergely Neu, Michal Valko
Most work on sequential learning assumes a fixed set of actions that are available all the time. However, in practice, actions can consist of picking subsets of readings from senso…
Efficient learning by implicit exploration in bandit problems with side observations
Tomas Kocak, Gergely Neu, Michal Valko +1
We consider online learning problems under a partial observability model capturing situations where the information conveyed to the learner is between full information and bandit f…
Online learning with noisy side observations
Tomáš Kocák, Gergely Neu, Michal Valko
We propose a new partial-observability model for online learning problems where the learner, besides its own loss, also observes some noisy feedback about the other actions, depend…
Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning
Antoine Moulin, Gergely Neu, Luca Viano
We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm ach…