Continuous Control on MuJoCo Swimmer v4
362.4Total RewardPPO
Evaluation Results
| Method | Links | |
|---|---|---|
| PPOEvaluation Protocol=Converged2026.04 | 362.4 | |
| BPOEvaluation Protocol=Converged2026.04 | 354.6 | |
| SMFPNFE=12026.05 | 137.2 | |
| DIMENFE=162026.05 | 118.8 | |
| QVPONFE=202026.05 | 112.4 | |
| SACEvaluation Protocol=Converged2026.04 | 102.7 | |
| SAC Flow-TNFE=42026.05 | 101.5 | |
| SAC Flow-GNFE=42026.05 | 98.2 | |
| MaxEntDPNFE=202026.05 | 90.3 | |
| PPONFE=12026.05 | 86.2 | |
| TD3NFE=12026.05 | 80.4 | |
| DPMDNFE=202026.05 | 80.2 | |
| SACNFE=12026.05 | 69.2 | |
| FPMD-RNFE=12026.05 | 62.2 | |
| QSMNFE=202026.05 | 61.6 | |
| SPONFE=12026.05 | 58.4 | |
| FPMD-MNFE=12026.05 | 55.4 | |
| DIPONFE=202026.05 | 52.2 | |
| FlowRLNFE=12026.05 | 48.7 |