We gave a high-level presentation on the topic of transfer in reinforcement learning. Here is the abstract: The reinforcement learning (RL) framework formalizes the problem of sequential decision-making under uncertainty. …
We presented ExTra-Learn at the “ANR Kick-off meeting” for the projects in the theme “Information treatment, human-machine interaction, and knowledge engineering”. Here you can find the presentation of the project, …
Daniele Calandriello presented “Sparse Multi-Task Reinforcement Learning” a joint work with M. Restelli (PoliMi). Abstract. In multi-task reinforcement learning (MTRL), the objective is to simultaneously learn multiple tasks and exploit …