Recent & Upcoming Talks

An overview of Social Reinforcement Learning, including multi-agent coordination, and using multi-agent training as a tool to induce emergent complexity and improve generalization.

This talk focuses on how social learning from other agents can lead to learning more complex behaviors and enhance generalization. I discuss recent work on emergent social learning and PsiPhi-Learning in detail.

A fun discussion of my research, career trajectory, and take on possible beneficial future directions for reinforcement learning research.

An overview of Social Reinforcement Learning including using multi-agent competition to drive emergent complexity via PAIRED, increasing multi-agent coordination with Social Influence, and learning from human feedback in dialog with Offline RL.

In addition to talking about Social Reinforcement Learning, I participated in a panel discussion with Deepak Pathak.

A talk entitled “Towards Social and Affective Machine Learning”, which covers most of the same content as my PhD defense, including my early PhD work on using multi-task learning for personalized wellbeing prediction.

My thesis defense at the MIT Media Lab. I cover work on Affective Computing, learning from affective signals in human-AI interaction, and multi-agent coordination. Includes an in-depth question period with my PhD committee.

This talk covers “Mechanisms for Generalized Machine Learning Across Tasks and Environments”, including a KL-control technique for combining reinforcement and supervised learning, and describes how to apply it to the problem of drug discovery.

A talk describing recent advances in AI and machine learning to a general tech audience, including some of my own work. For example, I discuss how to improve the output of a generative sketching model by monitoring people’s facial expression reactions to samples from the model.