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

DR19

Benchmarks

Task NameDataset NameSOTA ResultTrend
Offline Reinforcement LearningDR19 150-5-mid
NAUC57
4
Reinforcement Learning target performance estimationDR19 150-5-late
NAUC0.4
4
Offline In-Context Reinforcement LearningDR19-150-5 (complete)
NAUC64
4
Offline In-Context Reinforcement LearningDR19-300-5-early (test)
NAUC56
4
Showing 4 of 4 rows