Events
National Center for
Supercomputing Applications
University of Illinois at Urbana-Champaign
Contact us
National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign
Site
menu
Contact Us
About NCSA
Careers
Facilities
Directory
Research
Leadership
Business Office
User Support
Enabling Discovery
Delta
Blue Waters
Campus Cluster
Cybersecurity
Data
Software
Visualization
XSEDE
News
Press Room
Events
Get Updates
Industry
Expertise
Compute Resources
News & Stories
Contact
Search NCSA
Events
Home
News
Events
Events
National Center for Supercomputing Applications master calendar
Share on Facebook
Tweet
Email
add to calendar
contact
add an event
View Full Calendar
NCSA staff who would like to submit an item for the calendar can email
newsdesk@ncsa.illinois.edu
.
iDS^2 Mini-Workshop on Asymptotics and Non-Asymptotics in Control and Reinforcement Learning: Stochastic Control Problems, and How You Can Solve Yours
Event Type
Conference/Workshop
Sponsor
Coordinated Science Laboratory
Virtual
Date
Apr 16, 2021 12:30 - 3:00 pm with a break from 1:30 pm to 2:00 pm
Speaker
Sean Meyn (University of Florida)
Registration
Register here
Contact
Maxim Raginsky
E-Mail
maxim@illinois.edu
Views
75
Originating Calendar
Siebel School Speakers Calendar
Abstract:
Convergence theory for reinforcement learning is sparse: barely existent for Q-learning outside of the special case of Watkins, and the situation is even worse for RL with nonlinear function approximation. This is unfortunate, given the current interest in neural networks. What’s more, every user of RL knows that it can be insanely slow and unreliable. The talk will begin with explanations for slow convergence based on a combination of statistical reasoning and nonlinear dynamical systems theory. The special sauce in this lecture is an approach to universal stability of RL based on generalizations of Zap Q-learning.
Apologies in advance: there will be no finite-n bounds bounds in this lecture — all asymptotic. We will see why there is little hope for useful finite-n bounds when we consider algorithms with “noise” that has memory (such as in standard Markovian settings).
REFERENCES:
S. Chen, A. M. Devraj, F. Lu, A. Busic, and S. Meyn. Zap Q-Learning with nonlinear function approximation. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, and arXiv e-prints 1910.05405, volume 33, pages 16879–16890. Curran Associates, Inc., 2020.
A. M. Devraj, A. Busic and S. Meyn. Fundamental design principles for reinforcement learning algorithms. In K. G. Vamvoudakis, Y. Wan, F. L. Lewis, and D. Cansever, editors, Handbook on Reinforcement Learning and Control. Springer, 2021.
S. Meyn. Control Systems and Reinforcement Learning. Cambridge University Press, 2021 (draft available upon request)
link for robots only
About Cookies