Deep Reinforcement Learning on Seaquest Atari 2600
1,642IQM ReturnSpectral Routing
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Spectral RoutingReplay Strategy=Spectral Routing, Compute-Match status=false, Training Time (hr)=5.72026.04 | 1,642 | 42 | |
| REMReplay Strategy=Random Ensemble Mixture, Compute-Match status=false2026.04 | 1,550 | — | |
| PERReplay Strategy=Prioritized Experience Replay, Compute-Match status=false2026.04 | 1,525 | — | |
| Uniform ReplayReplay Strategy=Uniform, Compute-Match status=true2026.04 | 1,489 | — |