Social learning helps humans and animals rapidly adapt to new circumstances, and drives the emergence of complex learned behaviors. My research is focused on Social Reinforcement Learning—developing algorithms that combine insights from social learning and multi-agent training to improve AI agents' learning, generalization, coordination, and human-AI interaction.
I currently hold a joint position as a Senior Research Scientist at Google Brain and Visiting Postdoctoral Scholar at UC Berkeley. I received my PhD from MIT, where I worked on Affective Computing and deep/reinforcement/machine learning. For a brief overview of my thesis, check out this write-up in Computer Vision News. I have interned at DeepMind, Google Brain, and worked as an OpenAI Scholars mentor. I am currently on the faculty job market.
PhD in the Media Lab, 2019
Massachusetts Institute of Technology
MSc in Computer Science, 2014
University of British Columbia
BSc in Computer Science, 2012
University of Regina
BA in Psychology, 2012
University of Regina
PAIRED trains an agent to generate environments that maximize regret between a pair of learning agents. This creates feasible yet challenging environments, which exploit weaknesses in the agents to make them more robust. PAIRED significantly improves generalization to novel tasks.
We train dialog models with interactive data from conversations with real humans, using a novel Offline RL technique based on KL-control. Rather than rely on manual ratings, we learn from implicit signals like sentiment, and show that this results in better performance.
Social influence is a unified mechanism for achieving coordination and communication in Multi-Agent Reinforcement Learning, through rewarding agents for having causal influence over other agents' actions, thus increasing mutual information between agents' actions. Optimizing for influence leads to agents learning emergent communication protocols. Unlike prior work, influence can be computed in a fully decentralized manner.
Traditional, one-size-fits-all machine learning models fail to account for individual differences in predicting wellbeing outcomes like stress, mood, and health. Instead, we personalize models to the individual using multi-task learning (MTL), employing hierarchical Bayes, kernel-based and deep neural network MTL models to improve prediction accuracy by 13-23%.