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

Sine reward function

Benchmarks

Task NameDataset NameSOTA ResultTrend
Regret MinimizationSine reward function synthetic (test)
Oracle Regret289.86
9
Regret MinimizationSine reward function weak adversaries Appendix A.7 (test)
Oracle Regret280.62
9
Showing 2 of 2 rows