PTeterwak/action-reward-models-data download history

PTeterwak/action-reward-models-data is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 135 times (54 in the last 7 days), and 135 times in total. It ranks #91,367 among datasets by monthly downloads.

Action Reward Models for Web Agents Minimal, self-contained repo for the action reward model (ARM) study: generate per-step candidate-action data from a web-agent policy, train two kinds of reward models on teacher labels, and use them to pick actions at inference time. Everything her

Open PTeterwak/action-reward-models-data on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.