Continual Reinforcement Learning on Room Task 1
-0.01Worst Transfer Average (W-bar)DDQN
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| DDQNAlgorithm=DDQN2026.05 | -0.01 | 0.02 | — | |
| Qreg+NWLUAlgorithm=Qreg+NWLU2026.05 | -0.01 | 0.01 | — | |
| PackNetAlgorithm=PackNet2026.05 | -0.07 | 0.03 | — | |
| EWCAlgorithm=EWC2026.05 | -0.08 | 0.03 | — | |
| MERAlgorithm=MER2026.05 | -0.12 | 0.05 | — | |
| QregAlgorithm=Qreg2026.05 | -0.13 | 0.03 | — | |
| PMAlgorithm=PM2026.05 | -0.39 | 0.14 | — | |
| L2Algorithm=L22026.05 | -0.42 | 0.04 | — | |
| DQNAlgorithm=DQN2026.05 | -0.5 | 0.07 | — | |
| DDQN2026.05 | — | — | 1.57 | |
| DQN2026.05 | — | — | -0.08 | |
| EWC2026.05 | — | — | 0.3 | |
| L22026.05 | — | — | 0.04 | |
| MER2026.05 | — | — | 0.92 | |
| PackNet2026.05 | — | — | 0.45 | |
| PM2026.05 | — | — | 0.03 | |
| Qreg2026.05 | — | — | 0.14 | |
| Qreg+NWLU2026.05 | — | — | 1.21 |