Online Reinforcement Learning on FishSwim DMControl (final)
641.01Normalized ReturnGoRL(FM)
Evaluation results
| Method | Links | |
|---|---|---|
| GoRL(FM)Seeds=5, Decoder=Flow-Matching2025.12 | 641.01 | |
| GoRL(Diff)Seeds=5, Decoder=Diffusion2025.12 | 608.61 | |
| PPOSeeds=52025.12 | 433.7 | |
| FPOSeeds=52025.12 | 204.66 | |
| DPPOSeeds=52025.12 | 143.52 |