Offline Safe Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
0.74Normalized Reward
5
Mar 25, 2026
68Normalized Reward
5
Mar 25, 2026
0.54Normalized Reward
5
Mar 25, 2026
270.45Reward
4
Jul 7, 2026
243.63Reward
4
Jul 7, 2026
253.58Reward
4
Jul 7, 2026
257.98Reward
4
Jul 7, 2026
237.75Reward
4
Jul 7, 2026
236.57Reward
4
Jul 7, 2026
242.75Reward
4
Jul 7, 2026
316.47Reward
4
Jul 7, 2026
326.06Reward
4
Jul 7, 2026