Welcome to the Social Reinforcement Learning lab website!
Social learning helps humans and animals learn complex behavior, rapidly adapt to new circumstances, and cooperate to achieve joint goals. Our lab is focused on whether Social Reinforcement Learning—algorithms that leverage social information in both human-AI and multi-agent interactions—can do the same thing for AI. Research areas include multi-agent reinforcement learning, learning from human feedback (RLHF), human-AI interaction and cooperation, social learning, modeling other agents’ goals and preferences, and emergent complexity.
Our lab was founded by Natasha Jaques in 2024 and is part of the Paul G. Allen School for Computer Science and Engineering at the University of Washington.
If you are a prospective Ph.D student or postdoc, please visit the contact page for more information on how to apply.
News
- Our papers, VPL and GAMMA were accepted to NeurIPS. VPL was accepted as a spotlight!
- NeurIPS Concordia Contest launched: https://www.cooperativeai.com/contests/concordia-2024
- New paper on following ambiguous human instructions with social and embodied reasoning released!
- PhD students KJ and Mickel joined the lab!
- New paper on pluralistic alignment of large language models - VPL released.
- Natasha taught a grad class on Social Reinforcement Learning.
- Natasha was on the National Security Institute's Game Changing Technologies podcast.
- Natasha gave a talk on RLHF to AI TeaTalk Singapore.
- Natasha participated as a panelist at the NeurIPS Melting Pot Competition: https://nips.cc/virtual/2023/83652.
- The SocialRL lab started up this Winter at the University of Washington! Welcome Natasha, Sriyash, Daphne, Yanming, Yancheng!