yuyr/webrl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Shaw 2024-11-15 09:59:57 +08:00 committed by GitHub
parent 576262903b
commit 70ffd62521
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
VAB-WebArena-Lite/README.md
View File

@ -1,5 +1,20 @@
# Setup for VAB-WebArena-Lite # Setup for VAB-WebArena-Lite
## Table of Contents
- [Brief Introduction](#brief-introduction)
- [Install](#install)
- [Setup WebArena-Lite Environments](#setup-webarena-lite-environments)
- [🚨 Important: Refresh all websites before re-run another round of testing](#-important-refresh-all-websites-before-re-run-another-round-of-testing)
- [🖼️ Evaluating in VAB Standard Setting with SoM (Set-of-Marks) Visual Agents](#️-evaluating-in-vab-standard-setting-with-som-set-of-marks-visual-agents)
- [👎 Run Single Agent For Evalution](#-run-single-agent-for-evalution-slow-but-please-read-to-understand-meaning-of-arguments)
- [👍 Run Parallel Agent For Evaluation](#-run-parallel-agent-for-evaluation-recommended)
- [🚀 Evaluating in WebRL Setting (Text Modal)](#-evaluating-in-webrl-setting-text-modal)
- [Evaluation of Finetuned Models](#evaluation-of-finetuned-models)
- [Evaluation of Proprietary Models](#evaluation-of-proprietary-models)
- [Run Visualized Demostration](#run-visualized-demostration)
- [Acknowledgements](#acknowledgements)
## Brief Introduction ## Brief Introduction
VAB-WebArena-Lite is a 165-task refined subset from <a href="https://webarena.dev/" target="_blank">WebArena</a>. VAB-WebArena-Lite is a 165-task refined subset from <a href="https://webarena.dev/" target="_blank">WebArena</a>.