Reinforcement Learning on Energy System
709,280Training Steps (Mean)SHAC
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| SHACSafeguard=RM2025.06 | 709,280 | 579,920 | -8,793 | -12,685 | 0 | |
| PPOSafeguard=BP2025.06 | 661,577 | 457,426 | -2,293 | -3,421 | 0.3 | |
| PPOSafeguard=RM2025.06 | 548,352 | 313,344 | -339,006 | -485,334 | 0 | |
| SACSafeguard=BP2025.06 | 491,000 | 290,000 | -150,179 | -252,908 | 0 | |
| SHACSafeguard=BP2025.06 | 366,960 | 213,807 | -89,167 | -111,791 | 0 | |
| SACSafeguard=RM2025.06 | 355,999 | 187,974 | -1,843 | -2,396 | 0 |