School of Information Sciences Undergrad MASTER CALENDAR

View Full Calendar

The iSchool offers a number of events related to career and professional development, technology and information talks, research seminars, field trips, alumni panels, socials, and more. We also promote relevant opportunities on and around campus. 

We encourage students to also visit additional calendars and websites:

HandShake Events, Research Park, NCSA, Technology Entrepreneur Center (TEC),

The Career Center, Office of Undergraduate Research, Leadership Center, Siebel Center for Design,

Office of Technology Management, Center for Innovation in Teaching & Learning,

Applied Technologies for Learning in the Arts & Sciences.

National & International Scholar's Programs, Student Wellness

iSchool Calendars: Study Abroad Hours, iSchool Events, Non-iSchool Events

BSIS ICT Sessions, Express Advising

Portrait of Manxi Wu with header text that states "Colloquium on Digital Transformation Science" and talk title text that states "On Convergence and Stability of Coupled Belief – Strategy Learning Dynamics in Continuous Games." April 14, 2022 @ 1 p.m. PT/3 p.m. CT.

C3.ai DTI Colloquium: On Convergence and Stability of Coupled Belief – Strategy Learning Dynamics in Continuous Games

Event Type
Seminar/Symposium
Sponsor
C3.ai Digital Transformation Institute
Date
Apr 14, 2022   3:00 pm  
Speaker
Manxi Wu, UC Berkeley Postdoc Researcher
Registration
Required.
Contact
C3.ai Digital Transformation Institute
Views
3
Originating Calendar
NCSA-related events

C3.ai DTI's Colloquium on Digital Transformation is a series of weekly online talks on how artificial intelligence, machine learning, and big data can lead to scientific breakthroughs with large-scale societal benefits. Open to all – registration required.

Overview
We study a dynamic setting in which a public information platform updates a belief estimate of a continuous game parameter based on available data of strategies and payoffs. Players adjust their strategies by accounting for the repeatedly updated belief. The long-term behavior of the resulting stochastic learning dynamics is based on endogenous and non-i.i.d. data that is generated by players’ strategic decisions. We develop new tools to tackle the dynamic interplay between parameter learning and strategy learning in continuous games. We present results on the convergence and stability of such learning dynamics and develop conditions for convergence to complete information equilibrium. Furthermore, we apply this learning model to analyze the impact of information platforms on the strategic behavior of travelers in urban transportation systems. We show that our results can be used to design adaptive tolling mechanisms with travelers learning their routing decisions in traffic networks.

link for robots only