Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Offline Policy Adaptation on halfcheetah medium-expert

42.5Normalized Score

SRPO

15.77222.71129.6536.589Feb 5, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
42.5
2026.02
41.8
2026.02
39.5
2026.02
39.2
2026.02
38.6
2026.02
37.8
2026.02
37.7
2026.02
23.2
2026.02
21.1
2026.02
21.1
2026.02
20.8
2026.02
19.2
2026.02
18.6
2026.02
16.8