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

Offline Reinforcement Learning on D4RL Medium Hopper

109.4Normalized Score

RRPI

24.74446.72268.790.678Jun 9, 2023Nov 24, 2023May 10, 2024Oct 25, 2024Apr 11, 2025Sep 26, 2025Mar 14, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.03
109.4
2026.03
107.4
2026.03
106.8
2023.10
106.8
2023.10
105
2023.10
103.6
2023.10
102.1
2023.10
101.6
2026.03
101.3
2026.03
100.6
2023.06
98.5
2025.12
98.4
2025.12
97.9
2025.12
97.6
2025.12
97.2
2023.10
97.2
2023.06
95.4
2026.03
95.4
2023.10
92.8
2026.03
90.5
2026.03
90.3
2026.03
87
2023.06
85.7
2023.10
85.6
2026.03
84
2023.06
83.5
2023.06
81.2
2026.03
80.7
2023.06
79.3
2025.12
79.3
2023.06
77.4
2023.06
76.6
2026.03
74.3
2026.03
71.7
2023.06
67.6
2025.12
67.6
2023.06
67.6
2026.03
67.6
2023.06
66.3
2026.03
66.3
2023.10
66.3
2023.06
63.4
2023.06
63.1
2025.12
63.1
2023.06
62.2
2026.03
61.9
2025.12
61.2
2023.06
61.1
2023.06
61.1
2026.03
61.1
2023.06
58.5
2023.06
58.5
2025.12
58.5
2026.03
58.5
2023.06
58
2023.06
57.7
2023.06
55.7
2023.06
52.9
2025.12
52.9
2026.03
52.9
2026.03
48.8
2023.06
38.1
2023.06
36.4
2026.03
28