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

Offline Reinforcement Learning on D4RL Gym hopper-medium

104.8Normalized Return

RORL

-3.46424.64352.7580.857Oct 4, 2021Jun 29, 2022Mar 25, 2023Dec 19, 2023Sep 12, 2024Jun 8, 2025Mar 4, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2022.06
104.8
2024.01
103.8
2022.06
103.6
2021.10
101.6
2022.06
101.6
2024.01
101.6
2021.10
100.3
2024.01
100.3
2024.01
100.2
2021.10
86.6
2024.01
86.6
2026.03
81.6
2025.11
80.9
2026.03
79.3
2026.03
78
2021.10
77.8
2025.11
77.3
2022.06
75.3
2025.11
74.2
2026.03
69.4
2026.03
67.6
2026.03
66.5
2026.03
66.3
2025.11
66.3
2026.03
64.5
2026.03
63.5
2021.10
61.9
2022.06
61.9
2021.10
59.4
2025.11
59.3
2025.11
58.5
2021.10
55.3
2021.10
54.1
2022.06
54.1
2024.01
54.1
2025.11
52.9
2021.10
52.6
2021.10
46.2
2021.10
0.8
2022.06
0.8
2021.10
0.7