Continuous Control on Gym MuJoCo Suite Aggregate
1.691IQMDR.Q
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DR.QEnvironment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 1.691 | 1.564 | 1.608 | |
| SimbaV2Environment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 1.637 | 1.616 | 1.617 | |
| CrossQEnvironment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 1.565 | 1.489 | 1.475 | |
| TD7Environment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 1.54 | 1.55 | 1.57 | |
| MR.QEnvironment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 1.499 | 1.488 | 1.465 | |
| TD3+OFEEnvironment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 1.261 | 1.293 | 1.322 | |
| FoGEnvironment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 1.242 | 1.261 | 1.196 | |
| TQCEnvironment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 1.143 | 1.163 | 1.137 | |
| REDQEnvironment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 1.135 | 1.188 | 1.16 | |
| SimBaEnvironment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 1.114 | 1.143 | 1.147 | |
| DroQEnvironment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 1.108 | 1.133 | 1.134 | |
| BROEnvironment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 1.071 | 1.071 | 1.101 | |
| TDMPC2Environment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 1.05 | 1.18 | 1.04 | |
| DreamerV3Environment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 0.72 | 0.81 | 0.76 | |
| PPOEnvironment Steps=1M, Number of Random Seeds=10, Normalization Protocol=TD3-normalized2026.05 | 0.41 | 0.412 | 0.447 |