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

Offline Reinforcement Learning on D4RL Adroit hammer-cloned

2,280Normalized Score

EPQ

-90.888524.6311,140.151,755.669Nov 15, 2025Dec 1, 2025Dec 17, 2025Jan 2, 2026Jan 18, 2026Feb 3, 2026Feb 20, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
2,280
2025.12
1,440
2026.02
1,110
2026.02
1,100
2026.02
670
2025.12
500
2025.12
210
2026.02
210
2026.02
200
2026.02
200
2025.12
150
2025.12
150
2026.02
140
2026.02
110
2026.02
100
2026.02
80
2025.12
70
2025.12
70
2025.12
60
2025.12
50
2025.12
30
2025.11
11.6
2025.11
11.1
2026.02
10
2025.11
8.9
2025.11
8
2025.11
1.1
2025.11
0.9
2025.11
0.3