Constrained Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
388.1Episodic Reward
8
Feb 26, 2026
276.3Episodic Reward
8
Feb 26, 2026
102.3Episodic Reward
8
Feb 26, 2026
89.2Episodic Reward
8
Feb 26, 2026
198.6Episodic Reward
8
Feb 26, 2026
110.5Episodic Reward
8
Feb 26, 2026
1,734.1Episodic Reward
8
Feb 26, 2026
217.6Episodic Reward
5
Feb 26, 2026
2,455.3Reward
4
Jul 1, 2026
1,610.7Reward
4
Jul 1, 2026
2,951.7Reward
4
Jul 1, 2026
3,177.6Reward
4
Jul 1, 2026
16Reward
4
Jul 1, 2026
18.6Reward
4
Jul 1, 2026
41.2Reward
4
Jul 1, 2026
0Violations
1
Feb 26, 2026