Continual Reinforcement Learning on Room Task 2
0.08Worst Transfer Average (W-bar)Qreg+NWLU
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Qreg+NWLUAlgorithm=Qreg+NWLU2026.05 | 0.08 | 0.02 | — | |
| PackNetAlgorithm=PackNet2026.05 | 0.06 | 0.02 | — | |
| QregAlgorithm=Qreg2026.05 | 0.01 | 0.03 | — | |
| EWCAlgorithm=EWC2026.05 | -0.01 | 0.04 | — | |
| MERAlgorithm=MER2026.05 | -0.05 | 0.03 | — | |
| DQNAlgorithm=DQN2026.05 | -0.06 | 0.07 | — | |
| DDQNAlgorithm=DDQN2026.05 | -0.11 | 0.03 | — | |
| PMAlgorithm=PM2026.05 | -0.11 | 0.09 | — | |
| L2Algorithm=L22026.05 | -0.11 | 0.04 | — | |
| DDQN2026.05 | — | — | 0.29 | |
| DQN2026.05 | — | — | 0.45 | |
| EWC2026.05 | — | — | 0.36 | |
| L22026.05 | — | — | 0.48 | |
| MER2026.05 | — | — | 0.45 | |
| PackNet2026.05 | — | — | 0.81 | |
| PM2026.05 | — | — | 0.56 | |
| Qreg2026.05 | — | — | 0.4 | |
| Qreg+NWLU2026.05 | — | — | 0.45 |