Seohong Park

[Pronunciation: "suh-hong" ("Seo" as in "Seoul")]

Hey! I'm a Ph.D. student at UC Berkeley advised by Sergey Levine. I'm interested in developing scalable reinforcement learning (RL) algorithms and understanding their mathematical properties. The question that drives me these days is: Is RL really scalable? More specifically, my goal is to make off-policy Q-learning scalable so that we can leverage previously collected data. To this end, I work on data-driven RL, unsupervised RL, and representation learning.

CV | Email | Twitter | Google Scholar | Github

Blog posts

Dual representations (Oct 2025)

Q-learning is not yet scalable (Jun 2025)

Publications
(*: equal contribution, see the CV for the full list)

Dual Goal Representations

Seohong Park*, Deepinder Mann*, Sergey Levine
Preprint
paper | code | thread | blog post

Horizon Reduction Makes RL Scalable

Seohong Park, Kevin Frans, Deepinder Mann, Benjamin Eysenbach, Aviral Kumar, Sergey Levine
NeurIPS 2025 (Spotlight)
paper | code | thread | blog post

Diffusion Guidance Is a Controllable Policy Improvement Operator

Kevin Frans*, Seohong Park*, Pieter Abbeel, Sergey Levine
Preprint
paper | code | thread

Flow Q-Learning

Seohong Park, Qiyang Li, Sergey Levine
ICML 2025
paper | code | thread | project page

OGBench: Benchmarking Offline Goal-Conditioned RL

Seohong Park, Kevin Frans, Benjamin Eysenbach, Sergey Levine
ICLR 2025
paper | code | thread | project page

Unsupervised-to-Online Reinforcement Learning

Junsu Kim*, Seohong Park*, Sergey Levine
Preprint
paper | thread

Is Value Learning Really the Main Bottleneck in Offline RL?

Seohong Park, Kevin Frans, Sergey Levine, Aviral Kumar
NeurIPS 2024
ICML 2024 ARLET Workshop (Oral)
paper | thread | talk (10 min) | blog post

Foundation Policies with Hilbert Representations

Seohong Park, Tobias Kreiman, Sergey Levine
ICML 2024
paper | code | thread | project page

Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings

Kevin Frans, Seohong Park, Pieter Abbeel, Sergey Levine
ICML 2024 (Spotlight)
paper | code | thread | project page

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction

Seohong Park, Oleh Rybkin, Sergey Levine
ICLR 2024 (Oral)
paper | code | thread | talk (15 min) | project page

HIQL: Offline Goal-Conditioned RL with Latent States as Actions

Seohong Park, Dibya Ghosh, Benjamin Eysenbach, Sergey Levine
NeurIPS 2023 (Spotlight)
paper | code | thread | talk (5 min) | project page

Controllability-Aware Unsupervised Skill Discovery

Seohong Park, Kimin Lee, Youngwoon Lee, Pieter Abbeel
ICML 2023
paper | code1 | code2 | thread | project page

Predictable MDP Abstraction for Unsupervised Model-Based RL

Seohong Park, Sergey Levine
ICML 2023
paper | code | thread | project page

Lipschitz-constrained Unsupervised Skill Discovery

Seohong Park, Jongwook Choi*, Jaekyeom Kim*, Honglak Lee, Gunhee Kim
ICLR 2022
paper | code | thread | project page

Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods

Seohong Park, Jaekyeom Kim, Gunhee Kim
NeurIPS 2021
paper | code

Unsupervised Skill Discovery with Bottleneck Option Learning

Jaekyeom Kim*, Seohong Park*, Gunhee Kim
ICML 2021
paper | code

Talks

Invited Talks

Scalable Data-Driven RL @ AIRe Lab, Carnegie Mellon University (Mar 2025)

Scalable Data-Driven RL @ RL Lab, Princeton University (Mar 2025)

Scalable Data-Driven RL @ REAL Lab, Stanford University (Mar 2025)

Toward Scalable Unsupervised RL @ Intel AI Lab (Feb 2024)

Unsupervised Reinforcement Learning @ Reading group on Unsupervised RL, MILA (Apr 2023)

Education

University of California, Berkeley (Aug 2022 - Present)

Ph.D. student in Computer Science

Seoul National University (Mar 2014 - Aug 2022)

B.S. in Computer Science and Engineering
Leave of absence for military service: Sep 2017 - Sep 2020 (3 years)

The University of Tokyo (Sep 2016 - Feb 2017)

Exchange student

Work Experience

Devsisters (Sep 2018 - Sep 2020)

Machine Learning Engineer
Worked as part of the mandatory military service in the Republic of Korea

Ace Project (Sep 2017 - Aug 2018)

Software Engineer
Worked as part of the mandatory military service in the Republic of Korea

Honors and Awards

Scholarships

KFAS Overseas PhD Scholarship (Aug 2022 - Present)

Korea Foundation for Advanced Studies (KFAS)
Full tuition, insurance, and living expenses support for graduate studies

Berkeley Fellowship (Aug 2022 - Aug 2023)

Presidential Science Scholarship (Mar 2014 - Aug 2022)

Korea Student Aid Foundation (KOSAF)
Full tuition and living expenses support for undergraduate studies

Awards

Gold Prize (1st Place in Signal Processing), Samsung Humantech Paper Award (Jan 2022)

Programming Contests (Selected)

2nd Place, ACM-ICPC Asia Daejeon Regional Contest (Nov 2016)

1st Place, Google Code Jam Round 1C (May 2016)

3rd Place, ACM-ICPC Asia Daejeon Regional Contest (Nov 2015)

1st Place, ACM-ICPC Asia Daejeon Regional Preliminary Contest (Oct 2015)

1st Place, Korea Olympiad in Informatics (KOI) (Jul 2012)

Codeforces: polequoll

Coursework

Graduate Courses, UC Berkeley (Selected)

MATH 202A Introduction to Topology and Analysis

MATH 202B Introduction to Topology and Analysis

MATH 214 Differential Topology

MATH 240 Riemannian Geometry

MATH 250A Groups, Rings, and Fields

MATH 250B Commutative Algebra

MATH 256A Algebraic Geometry (Current)

MATH C218A/STAT C205A Probability Theory

STAT 210B Theoretical Statistics

CS 229A Information Theory and Coding

EE 227BT Convex Optimization

Template