EECS Special Seminar: Natasha Jaques "Social Reinforcement Learning"

Speaker: Natasha Jaques , Google Brain & UC Berkeley

Date: Thursday, March 31, 2022

Time: 2:00 PM to 3:00 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location: Grier A or zoom https://mit.zoom.us/j/96584991500?pwd=bzlNc2NZZjUrdGgxL0JpTTR0UEJPUT09

Event Type: Seminar

Room Description:

Host: Antonio Torralba, EECS

Contact: Fern D Keniston, fern@csail.mit.edu

Relevant URL:

Speaker URL: None

Speaker Photo:
Natasha jaques headshot

Reminders to: fern@csail.mit.edu

Reminder Subject: TALK: EECS Special Seminar: Natasha Jaques "Social Reinforcement Learning"

Abstract: Social learning helps humans and animals rapidly adapt to new circumstances, coordinate with others, and drives the emergence of complex learned behaviors. What if it could do the same for AI? This talk describes how Social Reinforcement Learning in multi-agent and human-AI interactions can address fundamental issues in AI such as learning and generalization, while improving social abilities like coordination. I propose a unified method for improving coordination and communication based on causal social influence. I then demonstrate that multi-agent training can be a useful tool for improving learning and generalization. I present PAIRED, in which an adversary learns to construct training environments to maximize regret between a pair of learners, leading to the generation of a complex curriculum of environments. Agents trained with PAIRED generalize more than 20x better to unknown test environments. Finally, I demonstrate the value of learning socially from interacting with other agents, whether those agents are AI or humans. Together, this work argues that Social RL is a valuable approach for developing more general, sophisticated, and cooperative AI, which is ultimately better able to serve human needs.

Bio: Natasha Jaques holds a joint position as a Senior Research Scientist at Google Brain and Visiting Postdoctoral Scholar at UC Berkeley. Her research focuses on Social Reinforcement Learning in multi-agent and human-AI interactions. Natasha completed her PhD at MIT, where her thesis received the Outstanding PhD Dissertation Award from the Association for the Advancement of Affective Computing. Her work has also received Best Demo at NeurIPS, an honourable mention for Best Paper at ICML, Best of Collection in the IEEE Transactions on Affective Computing, and Best Paper at the NeurIPS workshops on ML for Healthcare and Cooperative AI. She has interned at DeepMind, Google Brain, and was an OpenAI Scholars mentor. Her work has been featured in Science Magazine, Quartz, IEEE Spectrum, MIT Technology Review, Boston Magazine, and on CBC radio. Natasha earned her Masters degree from the University of British Columbia, and undergraduate degrees in Computer Science and Psychology from the University of Regina.

Research Areas:

Impact Areas:

This event is not part of a series.

Created by Fern D Keniston Email at Sunday, March 27, 2022 at 8:09 PM.