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

DR9

Benchmarks

Task NameDataset NameSOTA ResultTrend
Reinforcement Learning target performance estimationDR9 70-5-late
NAUC63
4
Reinforcement Learning target performance estimationDR9 40-1-late
NAUC33
4
Reinforcement Learning target performance estimationDR9 20-1-late
NAUC15
4
Offline In-Context Reinforcement LearningDR9 70-5-early (test)
NAUC50
4
Offline In-Context Reinforcement LearningDR9-40-1-early (test)
NAUC21
4
Showing 5 of 5 rows