Adding 1 to 2 human demonstrations improves web agent task success by 3.36 to 7.21 absolute percentage points on Mind2Web and VisualWebArena, though the best adapted agents still succeed less than 25% of the time.
Apprenticeship learning via inverse reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations
Adding 1 to 2 human demonstrations improves web agent task success by 3.36 to 7.21 absolute percentage points on Mind2Web and VisualWebArena, though the best adapted agents still succeed less than 25% of the time.