345 citations
- Microsoft (United States)US17 papers
- Microsoft Research Montréal (Canada)10 papers
- Carnegie Mellon UniversityUS4 papers
- Georgia Institute of TechnologyUS4 papers
- University College LondonGB4 papers
- University of Illinois Urbana-ChampaignUS4 papers
- Bellevue Hospital CenterUS3 papers
- McGill UniversityCA2 papers
- Microsoft Research New York City (United States)2 papers
- Microsoft Research (United Kingdom)GB2 papers
- Orange (France)FR2 papers
- Princeton UniversityUS2 papers
5 papers · 1 filter
Batched Bandits with Crowd Externalities
Romain Laroche, Othmane Safsafi, Raphael Feraud +1
In Batched Multi-Armed Bandits (BMAB), the policy is not allowed to be updated at each time step. Usually, the setting asserts a maximum number of allowed policy updates and the al…
Budgeted Reinforcement Learning in Continuous State Space
Nicolas Carrara, Edouard Leurent, Romain Laroche +3
A Budgeted Markov Decision Process (BMDP) is an extension of a Markov Decision Process to critical applications requiring safety constraints. It relies on a notion of risk implemen…
Deep Reinforcement Learning that Matters
Peter Henderson, Riashat Islam, Philip Bachman +3
In recent years, significant progress has been made in solving challenging problems across various domains using deep reinforcement learning (RL). Reproducing existing work and acc…
Learning Algorithms for Active Learning
Philip Bachman, Alessandro Sordoni, Adam Trischler
We introduce a model that learns active learning algorithms via metalearning. For a distribution of related tasks, our model jointly learns: a data representation, an item selectio…
Optimal Resource Allocation with Semi-Bandit Feedback
Tor Lattimore, Koby Crammer, Csaba Szepesvári
We study a sequential resource allocation problem involving a fixed number of recurring jobs. At each time-step the manager should distribute available resources among the jobs in…