explcre/tcod-v1-alfworld-data download history
explcre/tcod-v1-alfworld-data is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 489 times (176 in the last 7 days), and 3,391 times in total. It ranks #33,712 among datasets by monthly downloads.
TCOD-v1 ALFWorld data Trajectory data for the TCOD-v1 (temporal-curriculum on-policy distillation) ALFWorld experiments. Used to train the SFT behavior-cloning baseline and as the teacher-prefix source for TCOD-b2f. Files file rows description alfworld/teache