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

Reinforcement Learning on Hopper v4

27,721,263Average Return

pop-SAN

-1,105,367.566,378,469.2213,862,30621,346,142.78Jan 29, 2026Jan 30, 2026Jan 31, 2026Feb 1, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
27,721,263
2026.02
3,446,131
2026.02
3,410,164
2026.02
3,403,148
2026.02
3,385,157
2026.02
3,098,281
2026.02
356,568
2026.02
352,094
2026.01
3,462
2026.01
3,414
2026.01
3,384
2026.01
3,380
2026.01
3,349