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

Preference Estimation on PE-FD=6 (test)

56.91Average Outcome Reward

AREW– AS ONLY

2.091616.323330.55544.7867Mar 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
56.91
2026.03
54.65
2026.03
44.47
2026.03
42.1
2026.03
32.03
2026.03
12.47
2026.03
6
2026.03
5.7
2026.03
4.2