Continuous Control on MuJoCo HalfCheetah v4 (Average Return)
17,433Average ReturnTD7
Evaluation Results
| Method | Links | |
|---|---|---|
| TD7Environment Steps=1M, Number of Random Seeds=102026.05 | 17,433 | |
| FQL2025.09 | 15,969.59 | |
| SMFPNFE=12026.05 | 15,769.3 | |
| DDPG2025.09 | 15,628.1 | |
| SAC2025.09 | 15,476.83 | |
| TD32025.09 | 15,120.68 | |
| TDMPC2Environment Steps=1M, Number of Random Seeds=102026.05 | 15,078 | |
| SAC Flow-TNFE=42026.05 | 14,897.8 | |
| DR.QEnvironment Steps=1M, Number of Random Seeds=102026.05 | 14,775 | |
| TD3+OFEEnvironment Steps=1M, Number of Random Seeds=102026.05 | 13,758 | |
| BROEnvironment Steps=1M, Number of Random Seeds=102026.05 | 13,747 | |
| DIMENFE=162026.05 | 13,464.1 | |
| MR.QEnvironment Steps=1M, Number of Random Seeds=102026.05 | 12,939 | |
| DPMDNFE=202026.05 | 12,931.4 | |
| CrossQEnvironment Steps=1M, Number of Random Seeds=102026.05 | 12,893 | |
| SAC Flow-GNFE=42026.05 | 12,432.8 | |
| TQCEnvironment Steps=1M, Number of Random Seeds=102026.05 | 12,349 | |
| SimbaV2Environment Steps=1M, Number of Random Seeds=102026.05 | 12,022 | |
| FoGEnvironment Steps=1M, Number of Random Seeds=102026.05 | 11,709 | |
| REDQEnvironment Steps=1M, Number of Random Seeds=102026.05 | 11,505 | |
| MaxEntDPNFE=202026.05 | 11,281.5 | |
| DroQEnvironment Steps=1M, Number of Random Seeds=102026.05 | 11,070 | |
| FPMD-RNFE=12026.05 | 11,043.6 | |
| SACNFE=12026.05 | 10,616.9 | |
| TD3NFE=12026.05 | 10,388.6 | |
| FPMD-MNFE=12026.05 | 9,948.2 | |
| DIPONFE=202026.05 | 9,590.5 | |
| SimBaEnvironment Steps=1M, Number of Random Seeds=102026.05 | 9,422 | |
| FlowRLNFE=12026.05 | 8,963.4 | |
| QVPONFE=202026.05 | 8,759.4 | |
| MEOW2025.09 | 7,241.62 | |
| DreamerV3Environment Steps=1M, Number of Random Seeds=102026.05 | 5,502 | |
| PPONFE=12026.05 | 4,773.5 | |
| SPONFE=12026.05 | 4,008.2 | |
| QSMNFE=202026.05 | 3,888.2 | |
| PPOEnvironment Steps=1M, Number of Random Seeds=102026.05 | 1,744 |