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

Offline Reinforcement Learning on D4RL Gym halfcheetah-medium

74.8Normalized Return

SPQR

-3.82416.5883757.412Oct 1, 2021Jun 27, 2022Mar 23, 2023Dec 17, 2023Sep 11, 2024Jun 7, 2025Mar 4, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2024.01
74.8
2021.10
69.5
2021.10
67.5
2024.01
67.5
2022.06
66.8
2021.10
65.9
2022.06
65.9
2024.01
65.9
2022.06
64.9
2022.06
64.1
2021.10
60.7
2022.06
57.9
2021.10
55.2
2021.10
51.9
2026.03
51.2
2023.10
49.5
2025.11
49.5
2026.03
49.2
2021.10
49.1
49.1
2023.10
49.1
2026.03
49.1
2026.03
49.1
2021.10
49
2023.10
48.9
2023.10
48.7
2023.10
48.3
2025.11
48.3
2025.11
48.3
2025.11
47.7
2023.10
47.4
2026.03
47.4
2025.11
47.4
2021.10
46.9
2022.06
46.9
46.9
2023.10
46.9
2021.10
46.6
2021.10
44.4
2024.01
44.4
2024.06
44.2
2023.10
44.2
2023.10
44
2025.11
44
43.8
2021.10
43.7
2021.10
43.2
2022.06
43.2
2024.01
43.2
43
2026.03
42.9
2021.10
42.8
2023.10
42.6
2026.03
42.6
2025.11
42.6
2023.10
42.5
2026.03
42.5
2026.03
39.3
2021.10
39.2
2021.10
-0.8