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

Offline Policy Adaptation on hopper medium-expert

53.4Normalized Score

STC

9.40820.82932.2543.671Feb 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
53.4
2026.02
45.3
2026.02
26.4
2026.02
25.4
2026.02
22.3
2026.02
19.7
2026.02
19.1
2026.02
18.5
2026.02
18.3
2026.02
16.6
2026.02
15.9
2026.02
14.9
2026.02
14.4
2026.02
11.1