huzican/agent_envs download history

huzican/agent_envs is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 68 times (6 in the last 7 days), and 254 times in total. It ranks #149,549 among datasets by monthly downloads.

Agent Environment Task Sets (ALFWorld & ScienceWorld) Task sets for RL / OPD / RL+OPD runs on the Slime agent_envs stack. Rows are stored in the Slime-readable schema so train.py can load them directly with --input-key prompt --label-key label --metadata-key metadata. Row

Open huzican/agent_envs on Hugging Face

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