Locomotion on Ant IID (test)
2,240Mean Episode RewardDMAP
Evaluation Results
| Method | Links | |
|---|---|---|
| DMAPsigma=0.12022.09 | 2,240 | |
| DMAPsigma=0.1, protocol=train sigma = test sigma2022.09 | 2,240 | |
| Simplesigma=0.1, protocol=train sigma = test sigma2022.09 | 2,164 | |
| Oraclesigma=0.1, protocol=train sigma = test sigma2022.09 | 2,148 | |
| RMAsigma=0.1, protocol=train sigma = test sigma2022.09 | 2,138 | |
| DMAP-nesigma=0.1, protocol=train sigma = test sigma2022.09 | 1,966 | |
| Oraclesigma=0.3, protocol=train sigma = test sigma2022.09 | 1,723 | |
| RMAsigma=0.3, protocol=train sigma = test sigma2022.09 | 1,700 | |
| DMAPsigma=0.32022.09 | 1,623 | |
| DMAPsigma=0.3, protocol=train sigma = test sigma2022.09 | 1,623 | |
| DMAP-nesigma=0.3, protocol=train sigma = test sigma2022.09 | 1,542 | |
| Simplesigma=0.3, protocol=train sigma = test sigma2022.09 | 1,270 | |
| Oraclesigma=0.5, protocol=train sigma = test sigma2022.09 | 974 | |
| RMAsigma=0.5, protocol=train sigma = test sigma2022.09 | 966 | |
| DMAPsigma=0.52022.09 | 960 | |
| DMAPsigma=0.5, protocol=train sigma = test sigma2022.09 | 960 | |
| TCNsigma=0.12022.09 | 932 | |
| TCNsigma=0.1, protocol=train sigma = test sigma2022.09 | 932 | |
| DMAP-nesigma=0.5, protocol=train sigma = test sigma2022.09 | 881 | |
| TCNsigma=0.52022.09 | 481 | |
| TCNsigma=0.5, protocol=train sigma = test sigma2022.09 | 481 | |
| Simplesigma=0.5, protocol=train sigma = test sigma2022.09 | 391 | |
| TCNsigma=0.32022.09 | 251 | |
| TCNsigma=0.3, protocol=train sigma = test sigma2022.09 | 251 |