Deep Reinforcement Learning on SpaceInvaders Atari 2600
1,028IQM ReturnSpectral Routing
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Spectral RoutingReplay Strategy=Spectral Routing, Compute-Match status=false, Training Time (hr)=5.62026.04 | 1,028 | 38 | |
| REMReplay Strategy=Random Ensemble Mixture, Compute-Match status=false2026.04 | 958 | — | |
| PERReplay Strategy=Prioritized Experience Replay, Compute-Match status=false2026.04 | 931 | — | |
| Uniform ReplayReplay Strategy=Uniform, Compute-Match status=true2026.04 | 918 | — |