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

NIA Reward Function

Benchmarks

Task NameDataset NameSOTA ResultTrend
Cumulative Regret MinimizationNIA Reward Function Spec B: treatment-spillover interaction
Median Cumulative Regret243.4
3
Cumulative Regret MinimizationNIA Reward Function Spec A: saturation
Median Cumulative Regret333.5
3
Showing 2 of 2 rows