Broad Institute Models, Inference, and Algorithms (MIA) Seminar
Abstract
This talk covers “Mechanisms for Generalized Machine Learning Across Tasks and Environments”. In addition to personalized multi-task learning for healthcare, it introduces a KL-control technique for combining reinforcement and supervised learning, and describes how to apply it to the problem of drug discovery.
Date
2019
Location
Broad Institute
415 Main St, Cambridge, MA 02142
Natasha Jaques
My research is focused on Social Reinforcement Learning–developing algorithms that use insights from social learning to improve AI agents’ learning, generalization, coordination, and human-AI interaction.