[Colloquium] Today at 10:30 am ~ MLS Series ~ Zhaoran Wang

[Annie Simmons]

University of Chicago and Toyota Technological Institute at Chicago
Machine Learning Seminar Series


Zhaoran Wang
Northwestern

Friday, December 6 10:30 - 11:30 am
TTIC, Rm 526


Title:
On the Computational and Statistical Efficiency of Policy Optimization in (Deep) Reinforcement Learning

Abstract:
Coupled with powerful function approximators such as neural networks, policy optimization plays a key role in the tremendous empirical successes of deep reinforcement learning. In sharp contrast, the theoretical understandings of policy optimization remain rather limited from both the computational and statistical perspectives. From the perspective of computational efficiency, it remains unclear whether policy optimization converges to the globally optimal policy in a finite number of iterations, even given infinite data. From the perspective of statistical efficiency, it remains unclear how to attain the globally optimal policy with a finite regret or sample complexity.
 
To address the computational question, I will show that, under suitable conditions, natural policy gradient/proximal policy optimization/trust-region policy optimization (NPG/PPO/TRPO) converges to the globally optimal policy at a sublinear rate, even when it is coupled with neural networks. To address the statistical question, I will present an optimistic variant of NPG/PPO/TRPO, namely OPPO, which incorporates exploration in a principled manner and attains a \sqrt{T}-regret.
 
(Joint work with Qi Cai, Chi Jin, Jason Lee, Boyi Liu, Zhuoran Yang)

Bio:
Zhaoran Wang is an assistant professor at Northwestern University, working at the interface of machine learning, statistics, and optimization. He is the recipient of the AISTATS (Artificial Intelligence and Statistics Conference) notable paper award, ASA (American Statistical Association) best student paper in statistical learning and data mining, INFORMS (Institute for Operations Research and the Management Sciences) best student paper finalist in data mining, and the Microsoft fellowship.
Host: Mladen Kolar     




















Annie Simmons
Project Assistant IV
Computer Science Department
John Crerar Library Building
5730 S. Ellis
Chicago, IL 60637 
773.834.2750
773.702.8487
simmons3 at cs.uchicago.edu

“The dream is free the hustle is sold separately"

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20191206/362bc7ae/attachment-0002.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Zhaoran Wang.pdf
Type: application/pdf
Size: 1200577 bytes
Desc: not available
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20191206/362bc7ae/attachment-0001.pdf>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20191206/362bc7ae/attachment-0003.html>