Continual Reinforcement Learning on Room Task 3
0.2Worst Transfer Average (W-bar)Qreg+NWLU
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Qreg+NWLUAlgorithm=Qreg+NWLU2026.05 | 0.2 | 0.01 | — | |
| QregAlgorithm=Qreg2026.05 | 0.07 | 0.03 | — | |
| EWCAlgorithm=EWC2026.05 | 0.05 | 0.03 | — | |
| PMAlgorithm=PM2026.05 | 0.03 | 0.01 | — | |
| DDQNAlgorithm=DDQN2026.05 | -0.04 | 0.02 | — | |
| PackNetAlgorithm=PackNet2026.05 | -0.05 | 0.04 | — | |
| L2Algorithm=L22026.05 | -0.11 | 0.04 | — | |
| MERAlgorithm=MER2026.05 | -0.2 | 0.07 | — | |
| DQNAlgorithm=DQN2026.05 | -0.22 | 0.08 | — | |
| DDQN2026.05 | — | — | 25 | |
| DQN2026.05 | — | — | 38 | |
| EWC2026.05 | — | — | 68 | |
| L22026.05 | — | — | 78 | |
| MER2026.05 | — | — | 25 | |
| PackNet2026.05 | — | — | 66 | |
| PM2026.05 | — | — | 77 | |
| Qreg2026.05 | — | — | 80 | |
| Qreg+NWLU2026.05 | — | — | 63 |