OGBench: Benchmarking Offline Goal-Conditioned RL

A tidy lab notebook: one cornflower-blue syllable, a grid of little worlds, then plain prose under thin rules.

seohong.me/projects/ogbenchOGBench: Benchmarking Offline Goal-Conditioned RL
Screenshot of https://seohong.me/projects/ogbench/, © the authors. Shown for reference. Request removal
Venue
ICLR 2025
Year
2025
First author
Seohong Park
Field
reinforcement learning
Template
Bootstrap 3 personal-site template (partly from Michaël Gharbi and Jon Barron)
Theme
Light

Checked against the rendered page.

Why it is here

The two-weight wordmark logo, a tidy captioned environment grid and a centred one-line pitch make a confident first screen. A clear heading hierarchy and a code snippet block follow. Restrained and polished.

Overview

Color Palette

Typography

Source Sans 3
OGBench: Benchmarking Offline Goal-Conditioned RL Abstract · Method · Results · BibTeX — 0123456789
Source Code Pro
OGBench: Benchmarking Offline Goal-Conditioned RL Abstract · Method · Results · BibTeX — 0123456789

Spacing & Shape

Page Modules

Guidelines

More like this