Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
64.329Normalized Score
8
Mar 4, 2026
112.908Normalized Score
8
Mar 4, 2026
100.321Normalized Score
8
Mar 4, 2026
90.176Normalized Score
8
Mar 4, 2026
108.225Normalized Score
8
Mar 4, 2026
83.406Normalized Score
8
Mar 4, 2026
74.737Normalized Score
8
Mar 4, 2026
111.394Normalized Score
8
Mar 4, 2026
85.092Normalized Score
8
Mar 4, 2026
88.262Normalized Score
8
Mar 4, 2026
111.722Normalized Score
8
Mar 4, 2026
67.546Normalized Score
8
Mar 4, 2026
81.756Normalized Score
8
Mar 4, 2026
49.6Final Return
8
Feb 26, 2026
51.19Final Return
8
Feb 26, 2026
57.04Final Return
8
Feb 26, 2026
63.52Final Return
8
Feb 26, 2026
97Scene-v0 Score
8
Feb 26, 2026
57.3ant-large-v0
8
Feb 26, 2026
62.9Performance Score
8
Feb 26, 2026
48.6Performance Score
8
Feb 26, 2026
57.8Normalized Score
8
Feb 26, 2026
94.2Normalized Reward
8
Feb 26, 2026
11,170Normalized Reward
8
Feb 26, 2026
48.3Normalized Reward
8
Feb 26, 2026