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

Offline Reinforcement Learning on D4RL walker2d-medium-expert

116.1Normalized Score

PSPO

104.348107.399110.45113.501Jun 16, 2021Apr 9, 2022Feb 1, 2023Nov 26, 2023Sep 19, 2024Jul 14, 2025May 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.05
116.1
2026.03
115.7
2026.03
114.9
2026.05
114.9
2023.10
114.7
2026.03
114.4
2026.05
114.4
2023.10
114.2
2023.10
114.2
2021.06
112.9
2023.10
112.3
2026.03
112
2026.05
112
2026.03
111.9
2023.10
111.9
2026.05
111.9
2021.06
111.8
2024.04
111.7
2025.12
111.6
2023.06
111.6
2023.10
111.6
2021.10
111.2
2021.06
111
2021.06
110.9
2021.10
110.7
2021.10
110.7
2025.12
110.7
2025.12
110.7
2023.05
110.4
2024.04
110.4
2025.12
110.4
2026.03
110.4
2026.03
110.4
2026.02
110.2
2023.05
110.1
2026.02
110.1
2026.03
110.1
2021.10
109.7
2023.10
109.6
2023.06
109.6
2023.10
109.6
2026.03
109.6
2023.10
109.6
2025.09
109.6
2021.10
109.4
2026.02
109.2
2023.05
109.1
2026.03
109.1
2026.05
109.1
2026.02
109
2023.06
108.8
2023.06
108.8
2023.10
108.8
2024.05
108.8
108.8
2026.02
108.8
2023.06
108.8
2023.06
108.8
2026.03
108.8
2025.09
108.8
108.8
2023.06
108.7
2023.10
108.6
2025.09
108.6
2023.05
108.51
2026.03
108.5
2023.06
108.4
2023.10
108.4
2025.12
108.4
2025.09
108.4
2023.05
108.3
2026.02
108.3
2023.06
108.3
2023.10
108.2
2024.05
108.2
2023.06
108.1
2023.10
108.1
2025.12
108.1
2023.06
108.1
2026.03
108.1
108
2023.10
107.8
2023.05
107.8
2026.02
107.8
2023.10
107.7
2023.06
107.5
2023.10
107.5
2025.12
107.5
2026.03
107.5
2026.03
107.5
2026.05
107.5
2025.09
107.5
2023.06
107.4
2024.05
106.9
2026.03
106.9
2026.02
105.7
2024.04
105.4
2023.06
105.2
2024.04
105
2024.04
104.8
Showing 100 of 140 rows