Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Episodes

Benchmarks

Task NameDataset NameSOTA ResultTrend
Power grid survival management100 held-out episodes (val)
Mean Steps Achieved4,728
4
RecsplanationEpisodes
Faithfulness (Item)3.28
1
Interest profilingEpisodes
Coverage3.47
1
Showing 3 of 3 rows