MiniWoB++
Emerging5papers using it
2022first seen
The 'MiniWob++' dataset/benchmark contains a collection of web-based tasks designed to evaluate the performance of reinforcement learning agents in navigating graphical user interfaces using a unified action space.
Papers using MiniWoB++ (5)
- Cracking the Code of Action: a Generative Approach to Affordances for
Reinforcement LearningA Real-World WebAgent with Planning, Long Context Understanding, and
Program SynthesisUnderstanding HTML with Large Language ModelsWebWISE: Web Interface Control and Sequential Exploration with Large
Language ModelsSteP: Stacked LLM Policies for Web Actions