ResearchTasksPolicy optimization under non-exponential discountingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedTime-varying hyperbolic discounting Case 3 Exponential profile k3(t)PG-DPO0.007Global L1 Error5May 21, 2026Time-varying hyperbolic discounting Case 3 Sinusoidal profile k2(t)PG-DPO0.007Global L1 Error5May 21, 2026Time-varying hyperbolic discounting Case 3 Linear profile k1(t)PG-DPO0.006Global L1 Error5May 21, 2026
Time-varying hyperbolic discounting Case 3 Exponential profile k3(t)PG-DPO0.007Global L1 Error5May 21, 2026
Time-varying hyperbolic discounting Case 3 Sinusoidal profile k2(t)PG-DPO0.007Global L1 Error5May 21, 2026
Time-varying hyperbolic discounting Case 3 Linear profile k1(t)PG-DPO0.006Global L1 Error5May 21, 2026