Continual Reinforcement Learning on Room Task 5
0.01Worst Transfer Average (W-bar)Qreg
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| QregAlgorithm=Qreg2026.05 | 0.01 | 0.02 | — | |
| Qreg+NWLUAlgorithm=Qreg+NWLU2026.05 | -0.03 | 0.01 | — | |
| EWCAlgorithm=EWC2026.05 | -0.08 | 0.06 | — | |
| L2Algorithm=L22026.05 | -0.23 | 0.05 | — | |
| DQNAlgorithm=DQN2026.05 | -0.24 | 0.05 | — | |
| PMAlgorithm=PM2026.05 | -0.24 | 0.07 | — | |
| MERAlgorithm=MER2026.05 | -0.29 | 0.03 | — | |
| PackNetAlgorithm=PackNet2026.05 | -0.31 | 0.03 | — | |
| DDQNAlgorithm=DDQN2026.05 | -0.37 | 0.03 | — | |
| DDQN2026.05 | — | — | 0.11 | |
| DQN2026.05 | — | — | 0.61 | |
| EWC2026.05 | — | — | 0.37 | |
| L22026.05 | — | — | 0.05 | |
| MER2026.05 | — | — | 0.44 | |
| PackNet2026.05 | — | — | 0.04 | |
| PM2026.05 | — | — | 0.1 | |
| Qreg2026.05 | — | — | 0.23 | |
| Qreg+NWLU2026.05 | — | — | 0.04 |