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

Offline Reinforcement Learning on D4RL halfcheetah-random

45.4Normalized Score

ADMPO

-2.6489.82622.334.774Jun 12, 2021Mar 27, 2022Jan 10, 2023Oct 26, 2023Aug 9, 2024May 25, 2025Mar 10, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
45.4
2026.03
45.4
2025.12
42.5
2025.12
41.5
2023.10
41
2025.12
40
2023.10
40
2025.12
39.6
2026.03
39.5
2025.12
39.3
2021.10
38.9
2026.03
38.9
2023.10
38.8
2021.10
38.8
2021.10
38.8
2025.12
38.8
2023.10
38.8
2025.12
38.5
2026.03
37.8
2023.10
37.8
2023.10
37.6
2025.12
37
2025.12
36.5
2026.03
35.5
2021.10
35.4
2021.10
35.4
2021.06
35.4
2025.12
34.9
2023.10
33.7
2026.03
33
2025.12
32.8
2021.06
32.2
2021.10
31.3
2025.12
31.3
2026.03
31.3
2025.12
30.8
2025.12
29.9
2021.10
29.7
2021.10
29.1
2026.03
28.8
2021.10
28.4
2025.12
28.4
2023.10
28.4
2021.10
28
2023.10
26.7
2023.10
26.1
2021.10
25.6
2023.10
25.1
2021.10
24.5
2021.10
24.5
2021.10
24.3
2021.06
23.5
2023.10
22.4
2021.06
21.7
2021.10
19.6
2021.10
19.6
2023.10
15.1
2021.10
12.6
2023.10
11.6
2021.06
10.2
2022.06
7.9
2022.06
7.5
2021.06
6.9
2022.06
6.9
2022.06
6.7
2021.06
5.4
2022.06
4.6
2023.10
3.9
2023.10
3.9
2021.06
3.7
2021.10
2.3
2021.10
2.3
2021.10
2.3
2021.10
2.3
2023.10
2.2
2021.10
2.2
2021.10
2.2
2021.10
2.2
2021.10
2.2
2021.10
2.2
2021.10
2.2
2021.06
2.2
2021.06
2.2
2021.06
2
2021.10
-0.1
2021.10
-0.8