[Theory] NOW: [TTIC Talks] 4/29 Thesis Defense: Gene Li, TTIC

[Brandie Jones via Theory]

*When:     *Tuesday, April 29th at *10am CT*

*Where:*     Talk will be given *live, in-person* at

                       TTIC, 6045 S. Kenwood Avenue

                       5th Floor, *Room 529*


*Who*:       Gene Li, TTIC

*Title:       *Agnostic Reinforcement Learning: Foundations and Algorithms

*Abstract:*   Reinforcement Learning (RL) has demonstrated tremendous
empirical success across numerous challenging domains. However, we lack a
strong theoretical understanding of the statistical complexity of RL in
environments with large state spaces, where function approximation is
required for sample-efficient learning. This thesis addresses this gap by
rigorously examining the statistical complexity of RL with function
approximation from a learning theoretic perspective. Departing from a long
history of prior work, we consider the weakest form of function
approximation, called agnostic policy learning, in which the learner seeks
to find the best policy in a given class $\Pi$, with no guarantee that
$\Pi$ contains an optimal policy for the underlying task.

We systematically explore agnostic policy learning along three key axes:
environment access---how a learner collects data from the environment;
coverage conditions---intrinsic properties of the underlying MDP measuring
the expansiveness of state-occupancy measures for policies in the class
$\Pi$, and representational conditions--- structural assumptions on the
class $\Pi$ itself. Within this comprehensive framework, we (1) design new
learning algorithms with theoretical guarantees and (2) characterize
fundamental performance bounds of any algorithm. Our results reveal
significant statistical separations that highlight the power and
limitations of agnostic policy learning.

*Thesis Committee: *Nathan Srebro (Thesis Advisor), Avrim Blum, Akshay
Krishnamurthy, Cong Ma


Thanks,
Brandie


-- 
*Brandie Jones *
*Executive **Administrative Assistant*
Toyota Technological Institute
6045 S. Kenwood Avenue
Chicago, IL  60637
www.ttic.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20250429/8d818608/attachment.html>