ryan-superman/tcod-webshop-teacher-trajectories download history
ryan-superman/tcod-webshop-teacher-trajectories is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 74 times (26 in the last 7 days), and 74 times in total. It ranks #140,995 among datasets by monthly downloads.
WebShop teacher trajectories (GiGPO-Qwen2.5-7B-Instruct-WebShop) Expert trajectories on the WebShop 1000-product catalog, collected for the backward-to-forward (b2f) curriculum in TCOD/UOPD. Contents file rows what it is teacher_actions.jsonl 4369 one row per
Open ryan-superman/tcod-webshop-teacher-trajectories on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.