Counterfactual Policy Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
-776Lowest Cumulative Reward
2
Mar 4, 2026
-776Lowest Cumulative Reward
2
Mar 4, 2026
231Lowest Cumulative Reward
2
Mar 4, 2026
-87Lowest Cumulative Reward
2
Mar 4, 2026
-68Lowest Cumulative Reward
2
Mar 4, 2026
41Lowest Cumulative Reward
2
Mar 4, 2026
-9,050Lowest Cumulative Reward
2
Mar 4, 2026
100Lowest Cumulative Reward
2
Mar 4, 2026
8,000Lowest Cumulative Reward
2
Mar 4, 2026
-698Lowest Cumulative Reward
2
Mar 4, 2026
14Lowest Cumulative Reward
2
Mar 4, 2026
19Lowest Cumulative Reward
2
Mar 4, 2026
-698Lowest Cumulative Reward
2
Mar 4, 2026
-697Cumulative Reward (Lowest)
2
Mar 4, 2026
-495Lowest Cumulative Reward
2
Mar 4, 2026
221Avg Worst-Case V(s0)
2
Mar 4, 2026
37.3Average Worst-Case V(s0)
2
Mar 4, 2026
1,660Average Worst-Case Counterfactual V(s0)
2
Mar 4, 2026
230Worst-Case Counterfactual V(s0)
2
Mar 4, 2026
346Avg Worst-Case Counterfactual V(s0)
2
Mar 4, 2026