Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Policy learning from action-inclusive feedback on OpenML K ≥ 3
Loading...
57.98
Policy Accuracy
CB Policy
13.9568
25.3859
36.815
48.2441
Jun 16, 2022
Policy Accuracy
Constant Action
Performance vs CB
Updated 4d ago
Evaluation Results
Method
Method
Links
Policy Accuracy
Constant Action
Performance vs CB
CB Policy
2022.06
57.98
-
-
AI-IGL
Feedback=Action-Inclusive
2022.06
35.74
-
0.59
IGL (full CI)
Feedback=full CI
2022.06
15.65
-
0.3
Constant Action
2022.06
-
25.28
-
Feedback
Search any
task
Search any
task