All talks held in Pacific Time. **Schedule subject to change**

–
Coffee and Check-in
–
Opening Remarks
–
Talk By

Constantinos Daskalakis (Massachusetts Institute of Technology)
–
Break
–
Independent and Decentralized Learning in Markov Potential Games

Manxi Wu (Cornell University)
–
Breaking the Curse of Multiagency in Multi-Agent RL: Decentralized Function Approximation and Faster Convergence

Yu Bai (Salesforce Research)
–
Lunch
–
Reinforcement Learning Goes for Gold: How Policy Gradient Methods Converge to Winning Strategies in Stochastic Games

Emmanouil Vasileios Vlatakis Gkaragkounis (UC Berkeley)
–
Memory Bounds for Continual Learning

Binghui Peng (Columbia University)
–
Break
–
Collaboration Time
–
Reception
–
Coffee and Check-in
–
New perspectives on dynamical systems

Christos Papadimitriou (Columbia University)
–
Break
–
Statistical Contract Theory

Michael Jordan (University of California, Berkeley)
–
Repeated multi-unit auctions for carbon

Simina Branzei (Purdue University)
–
Lunch
–
Collaboration Time
–
Break
–
Collaboration Time
–
Coffee and Check-in
–
The statistical complexity of interactive decision making: A minimax optimization perspective

Dylan Foster (Microsoft Research)
–
Break
–
On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring.

Noah Golowich (MIT & Google)
–
Lunch
–
Optimizing in the Presence of Strategic Behavior

Eric Mazumdar (California Institute of Technology)
–
Break
–
Gaming the Learning

Amin Karbasi (Yale University)
–
Coffee and Check-in
–
Hybrid RL

Jason Lee (Princeton University)
–
Break
–
Making Minimax Optimization Adaptive and Reproducible

Niao He (ETH Zürich)
–
Lunch
–
Higher-Order Uncoupled Dynamics Do Not Lead to Nash Equilibrium - Except When They Do

Jeff S. Shamma (University of Illinois Urbana-Champaign)
–
Break
–
Collaboration Time