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

Offline Reinforcement Learning on D4RL hopper-random

53.6Normalized Score

MOREL

-1.20813.02127.2541.479Feb 16, 2021Dec 21, 2021Oct 25, 2022Aug 29, 2023Jul 2, 2024May 6, 2025Mar 10, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2021.10
53.6
2021.02
53.6
2026.03
38.1
2026.03
35
2026.03
32.7
2026.03
32.7
2023.10
32.7
2026.03
32.1
2023.10
31.8
2021.10
31.7
2021.10
31.7
2021.10
31.4
2021.10
31.4
2021.10
31.3
2023.10
30.7
2021.10
30.2
2021.10
30.2
2026.03
25.4
2021.10
25.3
2023.10
25.3
2026.03
20.4
2023.10
18.7
2023.10
17.9
2021.10
17.9
2021.02
17.9
2023.10
17.5
2023.10
17.5
2021.06
12.2
2021.02
12.2
2023.10
11.9
2021.02
11.7
2023.10
11.5
2023.10
11.4
2021.06
11.4
2021.02
11.4
2021.02
11.3
2023.10
11.2
2023.10
11.1
2021.06
11.1
2021.06
11
2021.02
11
2023.10
10.8
2021.10
10.8
2021.02
10.8
2023.10
10.7
2021.06
10.7
2023.10
10.6
2021.10
10
2021.10
9.9
2021.06
9.6
2021.06
9.5
2021.10
8.1
2021.10
8
2021.10
8
2021.10
7.9
2021.10
7.8
2021.06
7.8
2021.10
7.1
2023.10
7
2022.06
6.8
2021.10
6.7
2021.06
6.7
2022.06
6.7
2022.06
6.6
2022.06
6.5
2022.06
6.5
2021.06
5.6
2021.10
5.3
2026.03
5.3
2021.10
4.1
2021.10
3.7
2021.10
3.6
2021.10
3.4
2021.10
2.6
2021.06
2.6
2021.02
1.6
2021.10
0.9
2021.10
0.9