Once every week while school is in session, EECS invites a distinguished researcher or practitioner in a computer science or electrical and computer engineering-related field to present their ideas and/or work. Talks are generally targeted to electrical engineering and computer science graduate students. This colloquium series is free and open to everyone.

Upcoming Colloquia

AI Seminar: Estimating Long-term Rewards by Off-policy Reinforcement Learning

Wednesday, November 10, 2021 - 1:00pm to 2:00pm
https://oregonstate.zoom.us/j/93591935144?pwd=YjZaSjBYS0NmNUtjQzBEdzhPeDZ5UT09

Speaker Information

Lihong Li
Senior Principal Scientist
Amazon

Abstract

One of the core problems in reinforcement learning (RL) is estimating the long-term reward of a given policy. In many real-world applications such as healthcare, robotics and dialogue systems, running a new policy on users or robots can be costly or r.isky. This gives rise to the need for off-policy, or counterfactual, estimation: estimate the long-term reward of a given policy using data previously collected by another policy (e.g., the one currently deployed).  This talk will describe some recent advances in this problem, for which many standard estimators suffer an exponentially large variance (known as "the curse of horizon").  Our approach is based on a dual linear program formulation of the long-term reward, and can be extended to estimate confidence intervals.

Speaker Bio

Lihong Li is a Senior Principal Scientist at Amazon. He obtained a PhD degree in Computer Science from Rutgers University. After that, he held research positions in Yahoo!, Microsoft and Google, before joining Amazon. His main research interests are in reinforcement learning, including contextual bandits, and other related problems in AI. His work is often inspired by applications in recommendation, advertising, Web search and conversational systems. Homepage: http://lihongli.github.io.

Past Colloquia

Kaushik Jayaram
Friday, February 8, 2019 - 10:00am to 11:00am
Houssam Abbas
Monday, January 28, 2019 - 4:00pm to 4:50pm
Houssam Abbas
Wednesday, March 14, 2018 - 9:00am to 10:00am
Brian M. Kurkoski
Monday, November 20, 2017 - 4:00pm to 4:50pm
Amin Alipour
Monday, February 20, 2017 - 4:00pm to 4:50pm
Rene Just
Tuesday, March 10, 2015 - 10:00am to 11:00am
Arun Natarajan
Monday, October 29, 2012 - 4:00pm to 4:50pm

Pages