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

DR19-150-1

Benchmarks

Task NameDataset NameSOTA ResultTrend
Reinforcement Learning target performance estimationDR19-150-1 late
NAUC26
4
Offline In-Context Reinforcement LearningDR19-150-1 (complete)
NAUC31
4
Offline In-Context Reinforcement LearningDR19-150-1 early (test)
NAUC14
4
Showing 3 of 3 rows