We had four papers accepted at AI&Stats’17 on multi-armed bandit and reinforcement learning. The most interesting result is the first regret bound on learning in MDPs with options. For the …
We are going to present one novel parallel algorithm to perform alternating least squares for tensor completion applied to recommendation systems. Parallel Higher Order Alternating Least Square for Tensor Recommender …
We had two papers accepted at AI&Stats’16 on multi-armed bandit exploiting the arm structure to reduce the regret in reward maximization and the probability of error in best-arm identification. Online …
Alessandro Lazaric is giving an invited talk at the “Journée pour la promotion et le developpement de l’intelligence artificielle” organized by AfIA. Reinforcement Learning and Transfer of Knowledge Reinforcement learning …
We presented two novel results on apprenticeship learning at IJCAI’15, where we use demonstrations generated by an expert to learn near-optimal policies. This scenario is typical in source-to-target transfer, where the …
Alessandro Lazaric gave an invited talk on “Challenges of multi-task and transfer in reinforcement learning” at the “Machine Learning with Interdependent and Non-identically Distributed Data” seminar in Dagstuhl. [slides] [abstract]
Keywords: reinforcement learning, multi-armed bandit, transfer learning, exploration-exploitation, representation learning, hierarchical learning. Research Topic This main objective of this Ph.D. research project is to advance the state-of-the-art in the field of multi-armed …
We have presented novel results on how to exploit the structure of the arm set in multi-armed bandit. In particular, we consider the case where by pulling one action additional …
Marta Soare is presenting our preliminary work on “Multi-task Linear Bandits” together with Ouais Alsharif and Joelle Pineau (McGill University, Canada) at the second workshop on “Transfer and Multi-Task Learning: …
The paper on “Sparse Multi-Task Reinforcement Learning” in collaboration with D. Calandriello and M. Restelli (PoliMi) has been accepted for publication at NIPS’14. Abstract. In multi-task reinforcement learning (MTRL), the …
