SDS Seminar Series – Dr. Amy Zhang
Oct
20
2023
Oct
20
2023
Description
The Fall 2023 SDS Seminar Series continues on October 20th from 2:00 p.m. to 3:00 p.m. with Dr. Amy Zhang (Texas Instruments/Kilby Fellow in the Department of Electrical and Computer Engineering, University of Texas). This event is virtual.
Title: Bisimulation and Reinforcement Learning
Abstract: Most real world environments contain structure that would aid sample efficiency and generalization in control tasks if it were leveraged by algorithms. In this talk, we propose to incorporate different assumptions that better reflect the real world and allow the design of novel algorithms with theoretical guarantees to address this fundamental problem. We first present how state abstractions can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Our goal is to learn state abstractions that both provide for effective downstream control and invariance to task-irrelevant details. We use bisimulation metrics to quantify behavioral similarity between states, and learn robust latent representations which encode only the task-relevant information from observations. We provide theoretical guarantees for the learned approximate abstraction and extend this notion to multi-task settings.
Location
This virtual event requires software to participate. Get help with Zoom or Microsoft Teams.
Please contact Stat.admin@austin.utexas.edu for the zoom link.
Share
Other Events in This Series
Apr
3
2026
SDS Seminar Series – Leo Duan, University of Florida
Bayesian Distance-to-Set Models: from Latent Variable to Latent Projection
2:00 pm – 3:00 pm • In Person
Speaker(s): Leo Duan
Apr
17
2026
SDS Seminar Series – Rina Foygel Barber, University of Chicago
False Detection Rate Control in Time Series Coincidence Detection
2:00 pm – 3:00 pm • In Person
Speaker(s): Rina Foygel Barber
Sep
11
2026
SDS Seminar Series – Shuangjie Zhang, University of Texas at Austin
Structure Learning for Directed Trees with Zero-Inflated Compositional Nodes
2:00 pm – 3:00 pm • In Person
Speaker(s): Shuangjie Zhang
Sep
18
2026
SDS Seminar Series – Arhit Chakrabarti, University of Texas at Austin
Graphical Dirichlet Process for Clustering Non-Exchangeable Grouped Data
2:00 pm • In Person
Speaker(s): Arhit Chakrabarti
Sep
25
2026
SDS Seminar Series – Chad Hazlett, University of California, Los Angeles
The Synthetic Confounder: What Pre-Treatment Outcomes Can and Cannot Buy in Longitudinal Causal Inference
2:00 pm – 3:00 pm • In Person
Speaker(s): Chad Hazlett
Oct
2
2026
SDS Seminar Series – Giovanni Toto, University of Texas at Austin
Condition matrix completion for polypharmacy medication information
2:00 pm – 3:00 pm
Speaker(s): Giovanni Toto
Oct
9
2026
SDS Seminar Series – Anirban Bairagi University of Texas at Austin
TBA
2:00 pm – 3:00 pm
Speaker(s): Anirban Bairagi
Oct
16
2026
SDS Seminar Series – Adam Klivans, University of Texas at Austin
TBA
2:00 pm – 3:00 pm
Speaker(s): Adam Klivans
Oct
23
2026
SDS Seminar Series – Casey Breen, University of Texas at Austin
TBD
2:00 pm – 3:00 pm • In Person
Speaker(s): Casey Breen
Oct
30
2026
SDS Seminar Series – Sanjay Shakkottai, University of Texas at Austin
TBA
2:00 pm – 3:00 pm
Speaker(s): Sanjay Shakkottai