Skip to content
Advertisement
Tabular

pack_toothbrush_Nov19-advantages

Advantage Values for villekuosmanen/pack toothbrush Nov19 Pre-computed advantage values for offline RL training. Source Dataset: villekuosmanen/pack…

Advantage Values for villekuosmanen/pack toothbrush Nov19 Pre-computed advantage values for offline RL training. Source Dataset: villekuosmanen/pack toothbrush Nov19 Value Model: villekuosmanen/rewact toothbrush pistar 1.5.0 N-step lookahead: 50 Files This dataset contains per-episode parquet files with advantage values for each frame. Usage from pathlib import Path import pandas as pd Load advantages for a specific episode advantage df =… See the full description on the dataset page: toothbrush Nov19-advantages.

Source: Hugging Face Hub (villekuosmanen/pack_toothbrush_Nov19-advantages). Metadata imported from the dataset’s Hub tags.

Advertisement