ResearchTasksLinear off-policy predictionLinear off-policy predictionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedNew two-state environmentETD3.89Max RMSE8May 7, 2026Baird environmentTD2.21Max RMSE8May 7, 2026Two-state environmentGTD21.697Max RMSE8May 7, 2026