Continual Reinforcement Learning on Room Task 4
0.07Worst Transfer Grand Average (W-bar)Qreg
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| QregAlgorithm=Qreg2026.05 | 0.07 | 0.04 | — | |
| Qreg+NWLUAlgorithm=Qreg+NWLU2026.05 | 0.05 | 0.02 | — | |
| PMAlgorithm=PM2026.05 | 0.03 | 0.03 | — | |
| EWCAlgorithm=EWC2026.05 | -0.03 | 0.04 | — | |
| L2Algorithm=L22026.05 | -0.03 | 0.04 | — | |
| PackNetAlgorithm=PackNet2026.05 | -0.17 | 0.03 | — | |
| DQNAlgorithm=DQN2026.05 | -0.27 | 0.08 | — | |
| MERAlgorithm=MER2026.05 | -0.32 | 0.05 | — | |
| DDQNAlgorithm=DDQN2026.05 | -0.49 | 0.03 | — | |
| DDQN2026.05 | — | — | -0.06 | |
| DQN2026.05 | — | — | 0.78 | |
| EWC2026.05 | — | — | 0.64 | |
| L22026.05 | — | — | 0.65 | |
| MER2026.05 | — | — | 0.19 | |
| PackNet2026.05 | — | — | 0.3 | |
| PM2026.05 | — | — | 0.48 | |
| Qreg2026.05 | — | — | 0.63 | |
| Qreg+NWLU2026.05 | — | — | 0.24 |