Date & Time:
December 6, 2019 10:30 am – 11:30 am
TTIC 526, 6045 S. Kenwood Ave., Chicago, IL,
12/06/2019 10:30 AM 12/06/2019 11:30 AM America/Chicago Zhaoran Wang (Northwestern) – Computational and Statistical Efficiency of Policy Optimization UChicago CS/Toyota Technological Institute of Chicago Machine Learning Seminar Series TTIC 526, 6045 S. Kenwood Ave., Chicago, IL,

On the Computational and Statistical Efficiency of Policy Optimization in (Deep) Reinforcements Learning

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) 

Host: Mladen Kolar

Zhaoran Wang

Assistant Professor of Industrial Engineering and Management Sciences, Northwestern University

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.

Related News & Events

UChicago CS News

Non-Unital Noise Adds a New Wrinkle to the Quantum Supremacy Debate

Apr 05, 2024
In the News

The Science of Computer Security: An Interview with Grant Ho, Assistant Professor in Computer Science

Apr 02, 2024
UChicago CS News

Four Students Receive Honorable Mention in CRA Undergraduate Research Awards

Mar 25, 2024
UChicago CS News

Navigating the Intersection of Technology and Public Policy: The Journey of Ranya Sharma at UChicago

Mar 21, 2024
UChicago CS News

Assistant Professor Aloni Cohen Receives Prestigious Award for Groundbreaking Research in Machine Learning Complexity

Mar 20, 2024
UChicago CS News

Haifeng Xu named a AI2050 Early Career Fellow

Mar 11, 2024
UChicago CS News

FabRobotics: The Fusion of 3D Printing and Mobile Robots

Feb 27, 2024
UChicago CS News

Professor Andrew A. Chien on the Environmental Impacts of Technology

Feb 26, 2024
UChicago CS News

Assistant Professor Yanjing Li Awarded NSF CAREER Grant for Innovative Computer Architecture and Deep Learning Research

Feb 26, 2024
UChicago CS News

Prof. Rebecca Willett awarded the SIAG DATA Career prize

Feb 21, 2024
UChicago CS News

Argonne scientists use AI to identify new materials for carbon capture

Feb 19, 2024
UChicago CS News

Alumni Spotlight: Dixin Tang, Assistant Professor of Computer Science at UT Austin

Feb 05, 2024
arrow-down-largearrow-left-largearrow-right-large-greyarrow-right-large-yellowarrow-right-largearrow-right-smallbutton-arrowclosedocumentfacebookfacet-arrow-down-whitefacet-arrow-downPage 1CheckedCheckedicon-apple-t5backgroundLayer 1icon-google-t5icon-office365-t5icon-outlook-t5backgroundLayer 1icon-outlookcom-t5backgroundLayer 1icon-yahoo-t5backgroundLayer 1internal-yellowinternalintranetlinkedinlinkoutpauseplaypresentationsearch-bluesearchshareslider-arrow-nextslider-arrow-prevtwittervideoyoutube