Safe Offline Multi-Agent Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
0.56Reward
3
Jun 12, 2026
0.88Reward
3
Jun 12, 2026
82Reward
3
Jun 12, 2026
1.35Reward
3
Jun 12, 2026
0.13Reward
3
Jun 12, 2026
0.51Reward
3
Jun 12, 2026
1.11Reward (2halfcheetah)
3
Jun 12, 2026
0.4Reward
3
Jun 12, 2026
0.69Reward
3
Jun 12, 2026
0.99Reward
3
Jun 12, 2026
0.33Reward
3
Jun 12, 2026
0.6Reward
3
Jun 12, 2026
1.05Reward
3
Jun 12, 2026