Continuous Control on reacher
0.72Average RewardDDPG
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DDPGObservation Space=low-dimensional2015.09 | 0.72 | 0.987 | |
| DPGSetup=original with replay buffer and batch normalization2015.09 | 0.231 | 0.953 | |
| DDPGObservation Space=pixels2015.09 | 0.194 | 0.878 | |
| DynaMITE-RL2024.02 | -8.4 | — | |
| SecBAD2024.02 | -96.2 | — | |
| ContraBAR2024.02 | -101.6 | — | |
| VariBAD2024.02 | -102.4 | — | |
| BORel2024.02 | -103.5 | — | |
| RL^22024.02 | -150.6 | — |