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

Offline Reinforcement Learning on D4RL halfcheetah-medium-expert

110Normalized Score

VIPO

85.76892.05998.35104.641Jun 16, 2021Mar 31, 2022Jan 14, 2023Oct 30, 2023Aug 13, 2024May 29, 2025Mar 14, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
110-
2025.12
109.5-
2022.10
108.5-
2022.10
108.5-
2026.03
108.5-
2023.10
108.5-
2024.11
108.2-
2025.12
108.2-
2025.12
107.9-
2023.10
107.6-
2025.12
106.6-
2022.10
106.3-
2025.12
106.3-
2023.10
106.3-
2026.03
105.9-
2025.12
105.4-
2026.03
105.3-
2023.10
104.9-
2024.11
104.4-
2025.12
103.7-
2026.03
103.7-
2025.12
103.4-
2024.11
103.2-
2025.12
102.8-
2025.12
101.4-
2023.10
100-
2023.10
98.5-
2025.12
98.4-
2025.12
96.9-
2024.11
96.8-
2026.03
96.8-
2024.11
96.6-
2023.10
95.9-
95.7-
2025.12
95.7-
2026.03
95.7-
2021.10
95.6-
2026.03
95.4-
2022.10
95-
2022.10
95-
2023.06
95-
2024.04
95-
2025.12
95-
2023.06
95-
2026.03
95-
2026.03
95-
2023.10
94.8-
2023.10
94.8-
2024.04
94.7-
2025.12
94.4-
2025.12
93.7-
2023.10
93.7-
2021.06
93.5-
2023.06
93.5-
2026.02
93.1-
2026.02
92.7-
2021.10
92.6-
2026.02
92.6-
2026.03
92.5-
2023.06
91.9-
2023.06
91.8-
2021.06
91.7-
2023.06
91.6-
2026.02
91.6-
2023.06
91.6-
2026.03
91.6-
2023.06
91.5-
2023.10
91.1-
2026.03
91.1-
2021.10
91-
2021.10
90.8-
2025.12
90.8-
2026.02
90.7-
2023.06
90.6-
2024.05
90.6-
90.6-
2026.02
90.6-
2024.04
90.5-
2023.10
90-
2021.10
90-
2024.05
90-
2025.12
90-
2025.12
90-
2023.10
90-
2026.02
89.7-
2024.04
89.6-
2024.05
89.6-
2021.10
89.5-
2024.04
88.9-
2024.05
88.9-
2026.03
88.9-
2023.06
87.4-
2021.10
86.8-
2023.06
86.8-
2024.04
86.8-
2025.12
86.8-
2023.06
86.8-
2026.03
86.8-
2023.10
86.7-
2023.06
86.7-
Showing 100 of 172 rows