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

Offline Reinforcement Learning on D4RL antmaze-large (play)

90Normalized Score

FAC

-3.620.74569.3Oct 1, 2021Jun 27, 2022Mar 23, 2023Dec 17, 2023Sep 11, 2024Jun 7, 2025Mar 3, 2026
Updated 3mo ago

Evaluation Results

MethodLinks
2026.02
90
2026.02
84
2026.02
63.5
2026.02
60.4
2026.02
55.5
2026.02
53.6
2026.02
43.9
2026.02
40
2026.02
39.6
2021.10
23.6
2021.10
20.2
2026.02
15.8
2026.02
2.5
2021.10
2.2
2026.03
0.821
2026.03
0.813
2026.03
0.764
2026.03
0.635
2026.03
0.537
2026.03
0.396
2026.03
0.207
2026.02
0.2
2026.03
0.173
2026.03
0.067
2021.10
0
2021.10
0
2021.10
0
2021.10
0
2021.10
0
2021.10
0
2021.10
0
2021.10
0
2021.10
0
2021.10
0
2026.02
0
2026.03
0